mirror of
https://github.com/outbackdingo/optimclaw.git
synced 2026-08-26 23:50:17 +00:00
- Remove `pub use ironclaw_safety::*` from src/safety/mod.rs and migrate all 20+ call sites to import directly from `ironclaw_safety` - Remove `pub use ironclaw_skills::*` from src/skills/mod.rs and migrate all 15+ call sites to import directly from `ironclaw_skills` - Fix 4 clippy warnings: 2 shadow imports, 2 collapsible if-let chains - Add missing SkillActivated arm to WASM channel StatusUpdate match - Remove duplicate AuthRequired/AuthCompleted arms in repl.rs - Update CLAUDE.md extracted crates guidance and prompt template rule - Fix bench imports (safety_check, safety_pipeline) 46 files changed, zero warnings, 3836 tests passing. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
1324 lines
48 KiB
Rust
1324 lines
48 KiB
Rust
//! Agent-callable tools for managing skills (prompt-level extensions).
|
|
//!
|
|
//! Four tools for discovering, installing, listing, and removing skills
|
|
//! entirely through conversation, following the extension_tools pattern.
|
|
|
|
use std::sync::Arc;
|
|
|
|
use async_trait::async_trait;
|
|
|
|
use crate::context::JobContext;
|
|
use crate::tools::tool::{ApprovalRequirement, Tool, ToolError, ToolOutput, require_str};
|
|
use ironclaw_skills::catalog::SkillCatalog;
|
|
use ironclaw_skills::registry::SkillRegistry;
|
|
|
|
// ── skill_list ──────────────────────────────────────────────────────────
|
|
|
|
pub struct SkillListTool {
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
}
|
|
|
|
impl SkillListTool {
|
|
pub fn new(registry: Arc<std::sync::RwLock<SkillRegistry>>) -> Self {
|
|
Self { registry }
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Tool for SkillListTool {
|
|
fn name(&self) -> &str {
|
|
"skill_list"
|
|
}
|
|
|
|
fn description(&self) -> &str {
|
|
"List all loaded skills with their trust level, source, and activation keywords."
|
|
}
|
|
|
|
fn parameters_schema(&self) -> serde_json::Value {
|
|
serde_json::json!({
|
|
"type": "object",
|
|
"properties": {
|
|
"verbose": {
|
|
"type": "boolean",
|
|
"description": "Include extra detail (tags, content_hash, version)",
|
|
"default": false
|
|
}
|
|
}
|
|
})
|
|
}
|
|
|
|
async fn execute(
|
|
&self,
|
|
params: serde_json::Value,
|
|
_ctx: &JobContext,
|
|
) -> Result<ToolOutput, ToolError> {
|
|
let start = std::time::Instant::now();
|
|
let verbose = params
|
|
.get("verbose")
|
|
.and_then(|v| v.as_bool())
|
|
.unwrap_or(false);
|
|
|
|
let guard = self
|
|
.registry
|
|
.read()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
|
|
let skills: Vec<serde_json::Value> = guard
|
|
.skills()
|
|
.iter()
|
|
.map(|s| {
|
|
let mut entry = serde_json::json!({
|
|
"name": s.manifest.name,
|
|
"description": s.manifest.description,
|
|
"trust": s.trust.to_string(),
|
|
"source": format!("{:?}", s.source),
|
|
"keywords": s.manifest.activation.keywords,
|
|
});
|
|
|
|
if verbose && let Some(obj) = entry.as_object_mut() {
|
|
obj.insert(
|
|
"version".to_string(),
|
|
serde_json::Value::String(s.manifest.version.clone()),
|
|
);
|
|
obj.insert(
|
|
"tags".to_string(),
|
|
serde_json::json!(s.manifest.activation.tags),
|
|
);
|
|
obj.insert(
|
|
"content_hash".to_string(),
|
|
serde_json::Value::String(s.content_hash.clone()),
|
|
);
|
|
obj.insert(
|
|
"max_context_tokens".to_string(),
|
|
serde_json::json!(s.manifest.activation.max_context_tokens),
|
|
);
|
|
}
|
|
|
|
entry
|
|
})
|
|
.collect();
|
|
|
|
let output = serde_json::json!({
|
|
"skills": skills,
|
|
"count": skills.len(),
|
|
});
|
|
|
|
Ok(ToolOutput::success(output, start.elapsed()))
|
|
}
|
|
}
|
|
|
|
// ── skill_search ────────────────────────────────────────────────────────
|
|
|
|
pub struct SkillSearchTool {
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
catalog: Arc<SkillCatalog>,
|
|
}
|
|
|
|
impl SkillSearchTool {
|
|
pub fn new(
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
catalog: Arc<SkillCatalog>,
|
|
) -> Self {
|
|
Self { registry, catalog }
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Tool for SkillSearchTool {
|
|
fn name(&self) -> &str {
|
|
"skill_search"
|
|
}
|
|
|
|
fn description(&self) -> &str {
|
|
"Search for skills in the ClawHub catalog and among locally loaded skills."
|
|
}
|
|
|
|
fn parameters_schema(&self) -> serde_json::Value {
|
|
serde_json::json!({
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "Search query (name, keyword, or description fragment)"
|
|
}
|
|
},
|
|
"required": ["query"]
|
|
})
|
|
}
|
|
|
|
async fn execute(
|
|
&self,
|
|
params: serde_json::Value,
|
|
_ctx: &JobContext,
|
|
) -> Result<ToolOutput, ToolError> {
|
|
let start = std::time::Instant::now();
|
|
let query = require_str(¶ms, "query")?;
|
|
|
|
// Search the ClawHub catalog (async, best-effort)
|
|
let catalog_outcome = self.catalog.search(query).await;
|
|
let catalog_error = catalog_outcome.error.clone();
|
|
|
|
// Enrich top results with detail data (stars, downloads, owner)
|
|
let mut catalog_entries = catalog_outcome.results;
|
|
self.catalog
|
|
.enrich_search_results(&mut catalog_entries, 5)
|
|
.await;
|
|
|
|
// Search locally loaded skills
|
|
let installed_names: Vec<String> = {
|
|
let guard = self
|
|
.registry
|
|
.read()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
guard
|
|
.skills()
|
|
.iter()
|
|
.map(|s| s.manifest.name.clone())
|
|
.collect()
|
|
};
|
|
|
|
// Mark catalog entries that are already installed
|
|
let catalog_json: Vec<serde_json::Value> = catalog_entries
|
|
.iter()
|
|
.map(|entry| {
|
|
let is_installed = installed_names.iter().any(|n| {
|
|
// Match by slug suffix or exact name
|
|
entry.slug.ends_with(n.as_str()) || entry.name == *n
|
|
});
|
|
serde_json::json!({
|
|
"slug": entry.slug,
|
|
"name": entry.name,
|
|
"description": entry.description,
|
|
"version": entry.version,
|
|
"score": entry.score,
|
|
"installed": is_installed,
|
|
"stars": entry.stars,
|
|
"downloads": entry.downloads,
|
|
"owner": entry.owner,
|
|
})
|
|
})
|
|
.collect();
|
|
|
|
// Find matching local skills (simple substring match)
|
|
let query_lower = query.to_lowercase();
|
|
let local_matches: Vec<serde_json::Value> = {
|
|
let guard = self
|
|
.registry
|
|
.read()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
guard
|
|
.skills()
|
|
.iter()
|
|
.filter(|s| {
|
|
s.manifest.name.to_lowercase().contains(&query_lower)
|
|
|| s.manifest.description.to_lowercase().contains(&query_lower)
|
|
|| s.manifest
|
|
.activation
|
|
.keywords
|
|
.iter()
|
|
.any(|k| k.to_lowercase().contains(&query_lower))
|
|
})
|
|
.map(|s| {
|
|
serde_json::json!({
|
|
"name": s.manifest.name,
|
|
"description": s.manifest.description,
|
|
"trust": s.trust.to_string(),
|
|
})
|
|
})
|
|
.collect()
|
|
};
|
|
|
|
let mut output = serde_json::json!({
|
|
"catalog": catalog_json,
|
|
"catalog_count": catalog_json.len(),
|
|
"installed": local_matches,
|
|
"installed_count": local_matches.len(),
|
|
"registry_url": self.catalog.registry_url(),
|
|
});
|
|
if let Some(err) = catalog_error {
|
|
output["catalog_error"] = serde_json::Value::String(err);
|
|
}
|
|
|
|
Ok(ToolOutput::success(output, start.elapsed()))
|
|
}
|
|
}
|
|
|
|
// ── skill_install ───────────────────────────────────────────────────────
|
|
|
|
pub struct SkillInstallTool {
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
catalog: Arc<SkillCatalog>,
|
|
}
|
|
|
|
impl SkillInstallTool {
|
|
pub fn new(
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
catalog: Arc<SkillCatalog>,
|
|
) -> Self {
|
|
Self { registry, catalog }
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Tool for SkillInstallTool {
|
|
fn name(&self) -> &str {
|
|
"skill_install"
|
|
}
|
|
|
|
fn description(&self) -> &str {
|
|
"Install a skill from SKILL.md content, a URL, or by name from the ClawHub catalog."
|
|
}
|
|
|
|
fn parameters_schema(&self) -> serde_json::Value {
|
|
serde_json::json!({
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string",
|
|
"description": "Skill name or slug (from search results)"
|
|
},
|
|
"url": {
|
|
"type": "string",
|
|
"description": "Direct URL to a SKILL.md file"
|
|
},
|
|
"content": {
|
|
"type": "string",
|
|
"description": "Raw SKILL.md content to install directly"
|
|
}
|
|
},
|
|
"required": ["name"]
|
|
})
|
|
}
|
|
|
|
async fn execute(
|
|
&self,
|
|
params: serde_json::Value,
|
|
_ctx: &JobContext,
|
|
) -> Result<ToolOutput, ToolError> {
|
|
let start = std::time::Instant::now();
|
|
let name = require_str(¶ms, "name")?;
|
|
|
|
let content = if let Some(raw) = params.get("content").and_then(|v| v.as_str()) {
|
|
// Direct content provided
|
|
raw.to_string()
|
|
} else if let Some(url) = params
|
|
.get("url")
|
|
.and_then(|v| v.as_str())
|
|
.filter(|s| !s.is_empty())
|
|
{
|
|
// Fetch from explicit URL
|
|
fetch_skill_content(url).await?
|
|
} else {
|
|
// Look up in catalog and fetch
|
|
let download_url =
|
|
ironclaw_skills::catalog::skill_download_url(self.catalog.registry_url(), name);
|
|
fetch_skill_content(&download_url).await?
|
|
};
|
|
|
|
// Check for duplicates and get install_dir under a brief read lock.
|
|
let (user_dir, skill_name_from_parse) = {
|
|
let guard = self
|
|
.registry
|
|
.read()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
|
|
// Parse to extract the name (cheap, in-memory)
|
|
let normalized = ironclaw_skills::normalize_line_endings(&content);
|
|
let parsed = ironclaw_skills::parser::parse_skill_md(&normalized)
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?;
|
|
let skill_name = parsed.manifest.name.clone();
|
|
|
|
if guard.has(&skill_name) {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Skill '{}' already exists",
|
|
skill_name
|
|
)));
|
|
}
|
|
|
|
(guard.install_target_dir().to_path_buf(), skill_name)
|
|
};
|
|
|
|
// Perform async I/O (write to disk, validate round-trip) with no lock held.
|
|
let (skill_name, loaded_skill) =
|
|
ironclaw_skills::registry::SkillRegistry::prepare_install_to_disk(
|
|
&user_dir,
|
|
&skill_name_from_parse,
|
|
&ironclaw_skills::normalize_line_endings(&content),
|
|
)
|
|
.await
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?;
|
|
|
|
// Commit the in-memory addition under a brief write lock.
|
|
let installed_name = {
|
|
let mut guard = self
|
|
.registry
|
|
.write()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
guard
|
|
.commit_install(&skill_name, loaded_skill)
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?;
|
|
skill_name
|
|
};
|
|
|
|
let output = serde_json::json!({
|
|
"name": installed_name,
|
|
"status": "installed",
|
|
"trust": "installed",
|
|
"message": format!(
|
|
"Skill '{}' installed successfully. It will activate when matching keywords are detected.",
|
|
installed_name
|
|
),
|
|
});
|
|
|
|
Ok(ToolOutput::success(output, start.elapsed()))
|
|
}
|
|
|
|
fn requires_approval(&self, _params: &serde_json::Value) -> ApprovalRequirement {
|
|
ApprovalRequirement::UnlessAutoApproved
|
|
}
|
|
}
|
|
|
|
/// Validate that a URL is safe to fetch (SSRF prevention).
|
|
///
|
|
/// Rejects:
|
|
/// - Non-HTTPS URLs (except in tests)
|
|
/// - URLs pointing to private, loopback, or link-local IP addresses
|
|
/// - URLs without a host
|
|
pub fn validate_fetch_url(url_str: &str) -> Result<reqwest::Url, ToolError> {
|
|
let parsed = reqwest::Url::parse(url_str)
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Invalid URL '{}': {}", url_str, e)))?;
|
|
|
|
// Require HTTPS
|
|
if parsed.scheme() != "https" {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Only HTTPS URLs are allowed for skill fetching, got scheme '{}'",
|
|
parsed.scheme()
|
|
)));
|
|
}
|
|
|
|
let host = parsed
|
|
.host()
|
|
.ok_or_else(|| ToolError::ExecutionFailed("URL has no host".to_string()))?;
|
|
|
|
// Check if host is an IP address and reject private ranges.
|
|
// Use reqwest::Url host variants to get proper IpAddr values -- host_str()
|
|
// returns bracketed IPv6 (e.g. "[::1]") which IpAddr cannot parse.
|
|
// Unwrap IPv4-mapped IPv6 addresses (e.g. ::ffff:192.168.1.1) to catch
|
|
// SSRF bypasses that encode private IPv4 addresses as IPv6.
|
|
if let Some(ip) = host_ip_addr(&host) {
|
|
validate_fetch_ip(&ip, &host.to_string())?;
|
|
}
|
|
|
|
// Reject common internal hostnames, including FQDN forms with a trailing dot.
|
|
let host_lower = normalize_domain(host.to_string().as_str()).to_lowercase();
|
|
if host_lower == "localhost"
|
|
|| host_lower == "metadata.google.internal"
|
|
|| host_lower.ends_with(".internal")
|
|
|| host_lower.ends_with(".local")
|
|
{
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"URL points to an internal hostname: {}",
|
|
host
|
|
)));
|
|
}
|
|
|
|
Ok(parsed)
|
|
}
|
|
|
|
fn host_ip_addr(host: &url::Host<&str>) -> Option<std::net::IpAddr> {
|
|
match host {
|
|
url::Host::Ipv4(v4) => Some(std::net::IpAddr::V4(*v4)),
|
|
url::Host::Ipv6(v6) => Some(normalize_ip(std::net::IpAddr::V6(*v6))),
|
|
url::Host::Domain(_) => None,
|
|
}
|
|
}
|
|
|
|
fn normalize_ip(ip: std::net::IpAddr) -> std::net::IpAddr {
|
|
match ip {
|
|
std::net::IpAddr::V6(v6) => v6
|
|
.to_ipv4_mapped()
|
|
.map(std::net::IpAddr::V4)
|
|
.unwrap_or(std::net::IpAddr::V6(v6)),
|
|
other => other,
|
|
}
|
|
}
|
|
|
|
fn validate_fetch_ip(ip: &std::net::IpAddr, display_host: &str) -> Result<(), ToolError> {
|
|
if ip.is_loopback() || ip.is_unspecified() || is_private_ip(ip) || is_link_local_ip(ip) {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"URL points to a private/loopback/link-local address: {}",
|
|
display_host
|
|
)));
|
|
}
|
|
|
|
Ok(())
|
|
}
|
|
|
|
fn normalize_domain(host: &str) -> &str {
|
|
host.trim_end_matches('.')
|
|
}
|
|
|
|
fn validate_resolved_addrs(host: &str, addrs: &[std::net::SocketAddr]) -> Result<(), ToolError> {
|
|
if addrs.is_empty() {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"DNS resolution returned no addresses for {}",
|
|
host
|
|
)));
|
|
}
|
|
|
|
for addr in addrs {
|
|
let ip = normalize_ip(addr.ip());
|
|
validate_fetch_ip(&ip, host)?;
|
|
}
|
|
|
|
Ok(())
|
|
}
|
|
|
|
fn build_fetch_client_builder() -> reqwest::ClientBuilder {
|
|
reqwest::Client::builder()
|
|
.timeout(std::time::Duration::from_secs(15))
|
|
.user_agent("ironclaw/0.1")
|
|
.redirect(reqwest::redirect::Policy::none())
|
|
}
|
|
|
|
async fn build_safe_fetch_client(parsed: &reqwest::Url) -> Result<reqwest::Client, ToolError> {
|
|
let host = parsed
|
|
.host()
|
|
.ok_or_else(|| ToolError::ExecutionFailed("URL has no host".to_string()))?;
|
|
|
|
match host {
|
|
url::Host::Ipv4(_) | url::Host::Ipv6(_) => build_fetch_client_builder()
|
|
.build()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("HTTP client error: {}", e))),
|
|
url::Host::Domain(domain) => {
|
|
let lookup_host = normalize_domain(domain);
|
|
let port = parsed
|
|
.port_or_known_default()
|
|
.ok_or_else(|| ToolError::ExecutionFailed("URL has no valid port".to_string()))?;
|
|
|
|
let addrs: Vec<std::net::SocketAddr> = tokio::net::lookup_host((lookup_host, port))
|
|
.await
|
|
.map_err(|e| {
|
|
ToolError::ExecutionFailed(format!(
|
|
"DNS resolution failed for {}: {}",
|
|
lookup_host, e
|
|
))
|
|
})?
|
|
.collect();
|
|
|
|
validate_resolved_addrs(domain, &addrs)?;
|
|
|
|
build_fetch_client_builder()
|
|
.resolve_to_addrs(domain, &addrs)
|
|
.build()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("HTTP client error: {}", e)))
|
|
}
|
|
}
|
|
}
|
|
|
|
fn is_private_ip(ip: &std::net::IpAddr) -> bool {
|
|
match ip {
|
|
std::net::IpAddr::V4(v4) => {
|
|
// 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 169.254.0.0/16
|
|
v4.is_private() || v4.is_link_local()
|
|
}
|
|
std::net::IpAddr::V6(v6) => {
|
|
// Unique local (fc00::/7)
|
|
let segments = v6.segments();
|
|
(segments[0] & 0xfe00) == 0xfc00
|
|
}
|
|
}
|
|
}
|
|
|
|
fn is_link_local_ip(ip: &std::net::IpAddr) -> bool {
|
|
match ip {
|
|
std::net::IpAddr::V4(v4) => v4.is_link_local(),
|
|
std::net::IpAddr::V6(v6) => {
|
|
// fe80::/10
|
|
let segments = v6.segments();
|
|
(segments[0] & 0xffc0) == 0xfe80
|
|
}
|
|
}
|
|
}
|
|
|
|
/// Fetch SKILL.md content from a URL with SSRF protection.
|
|
///
|
|
/// The ClawHub registry returns skill downloads as ZIP archives containing
|
|
/// `SKILL.md` and `_meta.json`. This function detects ZIP responses (by the
|
|
/// `PK\x03\x04` magic bytes) and extracts `SKILL.md` automatically. Plain
|
|
/// text responses are returned as-is.
|
|
pub async fn fetch_skill_content(url: &str) -> Result<String, ToolError> {
|
|
let parsed = validate_fetch_url(url)?;
|
|
let client = build_safe_fetch_client(&parsed).await?;
|
|
|
|
let response = client.get(parsed.clone()).send().await.map_err(|e| {
|
|
ToolError::ExecutionFailed(format!("Failed to fetch skill from {}: {}", url, e))
|
|
})?;
|
|
|
|
if !response.status().is_success() {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Skill fetch returned HTTP {}: {}",
|
|
response.status(),
|
|
url
|
|
)));
|
|
}
|
|
|
|
// Limit download size to prevent memory exhaustion from large responses.
|
|
const MAX_DOWNLOAD_BYTES: usize = 10 * 1024 * 1024; // 10 MB
|
|
let bytes = response
|
|
.bytes()
|
|
.await
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Failed to read response body: {}", e)))?;
|
|
if bytes.len() > MAX_DOWNLOAD_BYTES {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Response too large: {} bytes (max {} bytes)",
|
|
bytes.len(),
|
|
MAX_DOWNLOAD_BYTES
|
|
)));
|
|
}
|
|
|
|
// Detect ZIP archive (PK\x03\x04 magic) and extract SKILL.md
|
|
let content = if bytes.starts_with(b"PK\x03\x04") {
|
|
extract_skill_from_zip(&bytes)?
|
|
} else {
|
|
String::from_utf8(bytes.to_vec()).map_err(|e| {
|
|
ToolError::ExecutionFailed(format!("Response is not valid UTF-8: {}", e))
|
|
})?
|
|
};
|
|
|
|
// Basic size check
|
|
if content.len() as u64 > ironclaw_skills::MAX_PROMPT_FILE_SIZE {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Skill content too large: {} bytes (max {} bytes)",
|
|
content.len(),
|
|
ironclaw_skills::MAX_PROMPT_FILE_SIZE
|
|
)));
|
|
}
|
|
|
|
Ok(content)
|
|
}
|
|
|
|
/// Extract `SKILL.md` from a ZIP archive returned by the ClawHub download API.
|
|
///
|
|
/// Walks ZIP local file headers looking for an entry named `SKILL.md`.
|
|
/// Supports Store (method 0) and Deflate (method 8) compression.
|
|
fn extract_skill_from_zip(data: &[u8]) -> Result<String, ToolError> {
|
|
use flate2::read::DeflateDecoder;
|
|
use std::io::Read;
|
|
|
|
// SKILL.md files should never be larger than 1 MB.
|
|
const MAX_DECOMPRESSED: usize = 1_024 * 1_024;
|
|
|
|
let mut offset = 0;
|
|
while offset + 30 <= data.len() {
|
|
// Local file header signature = PK\x03\x04
|
|
if data[offset..offset + 4] != [0x50, 0x4B, 0x03, 0x04] {
|
|
break;
|
|
}
|
|
|
|
let compression = u16::from_le_bytes([data[offset + 8], data[offset + 9]]);
|
|
let compressed_size = u32::from_le_bytes([
|
|
data[offset + 18],
|
|
data[offset + 19],
|
|
data[offset + 20],
|
|
data[offset + 21],
|
|
]) as usize;
|
|
let uncompressed_size = u32::from_le_bytes([
|
|
data[offset + 22],
|
|
data[offset + 23],
|
|
data[offset + 24],
|
|
data[offset + 25],
|
|
]) as usize;
|
|
let name_len = u16::from_le_bytes([data[offset + 26], data[offset + 27]]) as usize;
|
|
let extra_len = u16::from_le_bytes([data[offset + 28], data[offset + 29]]) as usize;
|
|
|
|
let name_start = offset + 30;
|
|
let name_end = name_start + name_len;
|
|
if name_end > data.len() {
|
|
break;
|
|
}
|
|
let file_name = std::str::from_utf8(&data[name_start..name_end]).unwrap_or("");
|
|
|
|
let data_start = name_end
|
|
.checked_add(extra_len)
|
|
.ok_or_else(|| ToolError::ExecutionFailed("ZIP header offset overflow".to_string()))?;
|
|
let data_end = data_start
|
|
.checked_add(compressed_size)
|
|
.ok_or_else(|| ToolError::ExecutionFailed("ZIP header size overflow".to_string()))?;
|
|
|
|
if file_name == "SKILL.md" {
|
|
if data_end > data.len() {
|
|
return Err(ToolError::ExecutionFailed(
|
|
"ZIP archive truncated".to_string(),
|
|
));
|
|
}
|
|
|
|
if uncompressed_size > MAX_DECOMPRESSED {
|
|
return Err(ToolError::ExecutionFailed(
|
|
"ZIP entry too large to decompress safely".to_string(),
|
|
));
|
|
}
|
|
|
|
let raw = &data[data_start..data_end];
|
|
let decompressed = match compression {
|
|
0 => raw.to_vec(), // Store
|
|
8 => {
|
|
// Deflate -- wrap with a read limit to guard against ZIP bombs
|
|
// where the declared size is small but decompressed output is huge.
|
|
let mut decoder = DeflateDecoder::new(raw).take(MAX_DECOMPRESSED as u64);
|
|
let mut buf = Vec::with_capacity(uncompressed_size.min(MAX_DECOMPRESSED));
|
|
decoder.read_to_end(&mut buf).map_err(|e| {
|
|
ToolError::ExecutionFailed(format!("Failed to decompress SKILL.md: {}", e))
|
|
})?;
|
|
buf
|
|
}
|
|
other => {
|
|
return Err(ToolError::ExecutionFailed(format!(
|
|
"Unsupported ZIP compression method: {}",
|
|
other
|
|
)));
|
|
}
|
|
};
|
|
|
|
return String::from_utf8(decompressed).map_err(|e| {
|
|
ToolError::ExecutionFailed(format!("SKILL.md in archive is not valid UTF-8: {}", e))
|
|
});
|
|
}
|
|
|
|
// Skip to next entry
|
|
offset = data_end;
|
|
}
|
|
|
|
Err(ToolError::ExecutionFailed(
|
|
"ZIP archive does not contain SKILL.md".to_string(),
|
|
))
|
|
}
|
|
|
|
// ── skill_remove ────────────────────────────────────────────────────────
|
|
|
|
pub struct SkillRemoveTool {
|
|
registry: Arc<std::sync::RwLock<SkillRegistry>>,
|
|
}
|
|
|
|
impl SkillRemoveTool {
|
|
pub fn new(registry: Arc<std::sync::RwLock<SkillRegistry>>) -> Self {
|
|
Self { registry }
|
|
}
|
|
}
|
|
|
|
#[async_trait]
|
|
impl Tool for SkillRemoveTool {
|
|
fn name(&self) -> &str {
|
|
"skill_remove"
|
|
}
|
|
|
|
fn description(&self) -> &str {
|
|
"Permanently remove an installed skill from disk. This action cannot be undone — \
|
|
the skill files will be deleted."
|
|
}
|
|
|
|
fn parameters_schema(&self) -> serde_json::Value {
|
|
serde_json::json!({
|
|
"type": "object",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string",
|
|
"description": "Name of the skill to remove"
|
|
}
|
|
},
|
|
"required": ["name"]
|
|
})
|
|
}
|
|
|
|
async fn execute(
|
|
&self,
|
|
params: serde_json::Value,
|
|
_ctx: &JobContext,
|
|
) -> Result<ToolOutput, ToolError> {
|
|
let start = std::time::Instant::now();
|
|
let name = require_str(¶ms, "name")?;
|
|
|
|
// Validate removal and get the filesystem path under a brief read lock.
|
|
let skill_path = {
|
|
let guard = self
|
|
.registry
|
|
.read()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
guard
|
|
.validate_remove(name)
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?
|
|
};
|
|
|
|
// Delete files from disk (async I/O, no lock held).
|
|
ironclaw_skills::registry::SkillRegistry::delete_skill_files(&skill_path)
|
|
.await
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?;
|
|
|
|
// Remove from in-memory registry under a brief write lock.
|
|
{
|
|
let mut guard = self
|
|
.registry
|
|
.write()
|
|
.map_err(|e| ToolError::ExecutionFailed(format!("Lock poisoned: {}", e)))?;
|
|
guard
|
|
.commit_remove(name)
|
|
.map_err(|e| ToolError::ExecutionFailed(e.to_string()))?;
|
|
}
|
|
|
|
let output = serde_json::json!({
|
|
"name": name,
|
|
"status": "removed",
|
|
"message": format!("Skill '{}' has been removed.", name),
|
|
});
|
|
|
|
Ok(ToolOutput::success(output, start.elapsed()))
|
|
}
|
|
|
|
fn requires_approval(&self, _params: &serde_json::Value) -> ApprovalRequirement {
|
|
ApprovalRequirement::Always
|
|
}
|
|
}
|
|
|
|
#[cfg(test)]
|
|
mod tests {
|
|
use super::*;
|
|
|
|
fn test_registry() -> Arc<std::sync::RwLock<SkillRegistry>> {
|
|
let dir = tempfile::tempdir().unwrap();
|
|
// Keep the tempdir so it lives for the test duration
|
|
let path = dir.keep();
|
|
Arc::new(std::sync::RwLock::new(SkillRegistry::new(path)))
|
|
}
|
|
|
|
fn test_catalog() -> Arc<SkillCatalog> {
|
|
Arc::new(SkillCatalog::with_url("http://127.0.0.1:1"))
|
|
}
|
|
|
|
#[test]
|
|
fn test_skill_list_schema() {
|
|
use crate::tools::tool::ApprovalRequirement;
|
|
let tool = SkillListTool::new(test_registry());
|
|
assert_eq!(tool.name(), "skill_list");
|
|
assert_eq!(
|
|
tool.requires_approval(&serde_json::json!({})),
|
|
ApprovalRequirement::Never
|
|
);
|
|
let schema = tool.parameters_schema();
|
|
assert!(schema.get("properties").is_some());
|
|
}
|
|
|
|
#[test]
|
|
fn test_skill_search_schema() {
|
|
use crate::tools::tool::ApprovalRequirement;
|
|
let tool = SkillSearchTool::new(test_registry(), test_catalog());
|
|
assert_eq!(tool.name(), "skill_search");
|
|
assert_eq!(
|
|
tool.requires_approval(&serde_json::json!({})),
|
|
ApprovalRequirement::Never
|
|
);
|
|
let schema = tool.parameters_schema();
|
|
assert!(schema["properties"].get("query").is_some());
|
|
}
|
|
|
|
#[test]
|
|
fn test_skill_install_schema() {
|
|
use crate::tools::tool::ApprovalRequirement;
|
|
let tool = SkillInstallTool::new(test_registry(), test_catalog());
|
|
assert_eq!(tool.name(), "skill_install");
|
|
assert_eq!(
|
|
tool.requires_approval(&serde_json::json!({})),
|
|
ApprovalRequirement::UnlessAutoApproved
|
|
);
|
|
let schema = tool.parameters_schema();
|
|
assert!(schema["properties"].get("name").is_some());
|
|
assert!(schema["properties"].get("url").is_some());
|
|
assert!(schema["properties"].get("content").is_some());
|
|
}
|
|
|
|
#[test]
|
|
fn test_skill_remove_schema() {
|
|
use crate::tools::tool::ApprovalRequirement;
|
|
let tool = SkillRemoveTool::new(test_registry());
|
|
assert_eq!(tool.name(), "skill_remove");
|
|
assert_eq!(
|
|
tool.requires_approval(&serde_json::json!({})),
|
|
ApprovalRequirement::Always
|
|
);
|
|
let schema = tool.parameters_schema();
|
|
assert!(schema["properties"].get("name").is_some());
|
|
}
|
|
|
|
#[test]
|
|
fn skill_remove_always_requires_approval_regardless_of_params() {
|
|
use crate::tools::tool::ApprovalRequirement;
|
|
let tool = SkillRemoveTool::new(test_registry());
|
|
|
|
let test_cases = vec![
|
|
("no params", serde_json::json!({})),
|
|
("empty name", serde_json::json!({"name": ""})),
|
|
(
|
|
"deployment skill",
|
|
serde_json::json!({"name": "deployment"}),
|
|
),
|
|
("custom skill", serde_json::json!({"name": "custom-skill"})),
|
|
(
|
|
"with extra fields",
|
|
serde_json::json!({"name": "skill", "extra": "field"}),
|
|
),
|
|
];
|
|
|
|
for (case_name, params) in test_cases {
|
|
assert_eq!(
|
|
tool.requires_approval(¶ms),
|
|
ApprovalRequirement::Always,
|
|
"skill_remove must always require approval for case: {}",
|
|
case_name
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_allows_https() {
|
|
assert!(super::validate_fetch_url("https://clawhub.ai/api/v1/download?slug=foo").is_ok());
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_http() {
|
|
let err = super::validate_fetch_url("http://example.com/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("Only HTTPS"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_private_ip() {
|
|
let err = super::validate_fetch_url("https://192.168.1.1/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("private"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_loopback() {
|
|
let err = super::validate_fetch_url("https://127.0.0.1/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("private"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_localhost() {
|
|
let err = super::validate_fetch_url("https://localhost/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("internal hostname"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_localhost_fqdn() {
|
|
let err = super::validate_fetch_url("https://localhost./skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("internal hostname"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_metadata_endpoint() {
|
|
let err =
|
|
super::validate_fetch_url("https://169.254.169.254/latest/meta-data/").unwrap_err();
|
|
assert!(err.to_string().contains("private"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_internal_domain() {
|
|
let err =
|
|
super::validate_fetch_url("https://metadata.google.internal/something").unwrap_err();
|
|
assert!(err.to_string().contains("internal hostname"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_file_scheme() {
|
|
let err = super::validate_fetch_url("file:///etc/passwd").unwrap_err();
|
|
assert!(err.to_string().contains("Only HTTPS"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_ipv4_mapped_ipv6_loopback() {
|
|
let err = super::validate_fetch_url("https://[::ffff:127.0.0.1]/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("private") || err.to_string().contains("loopback"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_fetch_url_rejects_ipv6_loopback() {
|
|
let err = super::validate_fetch_url("https://[::1]/skill.md").unwrap_err();
|
|
assert!(err.to_string().contains("private") || err.to_string().contains("loopback"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_resolved_addrs_rejects_loopback_hostname() {
|
|
let addrs = vec![
|
|
"127.0.0.1:443".parse::<std::net::SocketAddr>().unwrap(),
|
|
"[::1]:443".parse::<std::net::SocketAddr>().unwrap(),
|
|
];
|
|
|
|
let err = super::validate_resolved_addrs("example.com", &addrs).unwrap_err();
|
|
assert!(err.to_string().contains("private") || err.to_string().contains("loopback"));
|
|
}
|
|
|
|
#[test]
|
|
fn test_validate_resolved_addrs_allows_public_hostname() {
|
|
let addrs = vec![
|
|
"8.8.8.8:443".parse::<std::net::SocketAddr>().unwrap(),
|
|
"[2606:4700:4700::1111]:443"
|
|
.parse::<std::net::SocketAddr>()
|
|
.unwrap(),
|
|
];
|
|
|
|
assert!(super::validate_resolved_addrs("example.com", &addrs).is_ok());
|
|
}
|
|
|
|
#[test]
|
|
fn test_extract_skill_from_zip_deflate() {
|
|
// Build a real ZIP with flate2 + manual header construction.
|
|
use flate2::Compression;
|
|
use flate2::write::DeflateEncoder;
|
|
use std::io::Write;
|
|
|
|
let skill_md = b"---\nname: test\n---\n# Test Skill\n";
|
|
let mut encoder = DeflateEncoder::new(Vec::new(), Compression::default());
|
|
encoder.write_all(skill_md).unwrap();
|
|
let compressed = encoder.finish().unwrap();
|
|
|
|
let mut zip = Vec::new();
|
|
// Local file header
|
|
zip.extend_from_slice(&[0x50, 0x4B, 0x03, 0x04]); // signature
|
|
zip.extend_from_slice(&[0x14, 0x00]); // version needed (2.0)
|
|
zip.extend_from_slice(&[0x00, 0x00]); // flags
|
|
zip.extend_from_slice(&[0x08, 0x00]); // compression: deflate
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // mod time/date
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32 (unused)
|
|
zip.extend_from_slice(&(compressed.len() as u32).to_le_bytes()); // compressed size
|
|
zip.extend_from_slice(&(skill_md.len() as u32).to_le_bytes()); // uncompressed size
|
|
zip.extend_from_slice(&8u16.to_le_bytes()); // filename length
|
|
zip.extend_from_slice(&0u16.to_le_bytes()); // extra field length
|
|
zip.extend_from_slice(b"SKILL.md");
|
|
zip.extend_from_slice(&compressed);
|
|
|
|
let result = super::extract_skill_from_zip(&zip).unwrap();
|
|
assert_eq!(result, "---\nname: test\n---\n# Test Skill\n");
|
|
}
|
|
|
|
#[test]
|
|
fn test_extract_skill_from_zip_store() {
|
|
let skill_md = b"---\nname: stored\n---\n# Stored\n";
|
|
|
|
let mut zip = Vec::new();
|
|
// Local file header
|
|
zip.extend_from_slice(&[0x50, 0x4B, 0x03, 0x04]);
|
|
zip.extend_from_slice(&[0x0A, 0x00]); // version needed (1.0)
|
|
zip.extend_from_slice(&[0x00, 0x00]); // flags
|
|
zip.extend_from_slice(&[0x00, 0x00]); // compression: store
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // mod time/date
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
|
|
zip.extend_from_slice(&(skill_md.len() as u32).to_le_bytes()); // compressed = uncompressed
|
|
zip.extend_from_slice(&(skill_md.len() as u32).to_le_bytes());
|
|
zip.extend_from_slice(&8u16.to_le_bytes()); // filename length
|
|
zip.extend_from_slice(&0u16.to_le_bytes()); // extra field length
|
|
zip.extend_from_slice(b"SKILL.md");
|
|
zip.extend_from_slice(skill_md);
|
|
|
|
let result = super::extract_skill_from_zip(&zip).unwrap();
|
|
assert_eq!(result, "---\nname: stored\n---\n# Stored\n");
|
|
}
|
|
|
|
#[test]
|
|
fn test_extract_skill_from_zip_missing_skill_md() {
|
|
let mut zip = Vec::new();
|
|
zip.extend_from_slice(&[0x50, 0x4B, 0x03, 0x04]);
|
|
zip.extend_from_slice(&[0x0A, 0x00]); // version
|
|
zip.extend_from_slice(&[0x00, 0x00]); // flags
|
|
zip.extend_from_slice(&[0x00, 0x00]); // compression: store
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // mod time/date
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
|
|
zip.extend_from_slice(&2u32.to_le_bytes()); // compressed size
|
|
zip.extend_from_slice(&2u32.to_le_bytes()); // uncompressed size
|
|
zip.extend_from_slice(&10u16.to_le_bytes()); // filename length
|
|
zip.extend_from_slice(&0u16.to_le_bytes()); // extra field length
|
|
zip.extend_from_slice(b"_meta.json");
|
|
zip.extend_from_slice(b"{}");
|
|
|
|
let err = super::extract_skill_from_zip(&zip).unwrap_err();
|
|
assert!(err.to_string().contains("does not contain SKILL.md"));
|
|
}
|
|
|
|
// ── ZIP extraction security regression tests ────────────────────────
|
|
|
|
/// Helper: build a minimal ZIP local file header with Store compression.
|
|
fn build_zip_entry_store(file_name: &str, content: &[u8]) -> Vec<u8> {
|
|
let mut zip = Vec::new();
|
|
zip.extend_from_slice(&[0x50, 0x4B, 0x03, 0x04]); // signature
|
|
zip.extend_from_slice(&[0x0A, 0x00]); // version needed (1.0)
|
|
zip.extend_from_slice(&[0x00, 0x00]); // flags
|
|
zip.extend_from_slice(&[0x00, 0x00]); // compression: store (0)
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // mod time/date
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
|
|
zip.extend_from_slice(&(content.len() as u32).to_le_bytes()); // compressed size
|
|
zip.extend_from_slice(&(content.len() as u32).to_le_bytes()); // uncompressed size
|
|
zip.extend_from_slice(&(file_name.len() as u16).to_le_bytes()); // filename length
|
|
zip.extend_from_slice(&0u16.to_le_bytes()); // extra field length
|
|
zip.extend_from_slice(file_name.as_bytes());
|
|
zip.extend_from_slice(content);
|
|
zip
|
|
}
|
|
|
|
#[test]
|
|
fn test_zip_extract_valid_skill() {
|
|
let content = b"---\nname: hello\n---\n# Hello Skill\nDoes things.\n";
|
|
let zip = build_zip_entry_store("SKILL.md", content);
|
|
let result = super::extract_skill_from_zip(&zip).unwrap();
|
|
assert_eq!(result, std::str::from_utf8(content).unwrap());
|
|
}
|
|
|
|
#[test]
|
|
fn test_zip_extract_ignores_non_skill_entries() {
|
|
// ZIP with README.md and src/main.rs but no SKILL.md -- should error.
|
|
let mut zip = Vec::new();
|
|
zip.extend_from_slice(&build_zip_entry_store("README.md", b"# Readme"));
|
|
zip.extend_from_slice(&build_zip_entry_store("src/main.rs", b"fn main() {}"));
|
|
|
|
let err = super::extract_skill_from_zip(&zip).unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("does not contain SKILL.md"),
|
|
"Expected 'does not contain SKILL.md' error, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_zip_extract_path_traversal_rejected() {
|
|
// An entry named "../../SKILL.md" must NOT match the exact "SKILL.md" check.
|
|
let content = b"---\nname: evil\n---\n# Malicious path traversal\n";
|
|
let zip = build_zip_entry_store("../../SKILL.md", content);
|
|
|
|
let err = super::extract_skill_from_zip(&zip).unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("does not contain SKILL.md"),
|
|
"Path traversal entry should not match SKILL.md, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_zip_extract_nested_path_not_matched() {
|
|
// An entry named "subdir/SKILL.md" must NOT match the exact "SKILL.md" check.
|
|
let content = b"---\nname: nested\n---\n# Nested\n";
|
|
let zip = build_zip_entry_store("subdir/SKILL.md", content);
|
|
|
|
let err = super::extract_skill_from_zip(&zip).unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("does not contain SKILL.md"),
|
|
"Nested path should not match SKILL.md, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_zip_extract_oversized_rejected() {
|
|
// Create a ZIP entry whose declared uncompressed_size exceeds MAX_DECOMPRESSED (1 MB).
|
|
let oversized_claim: u32 = 2 * 1024 * 1024; // 2 MB
|
|
let small_body = b"tiny";
|
|
|
|
let mut zip = Vec::new();
|
|
zip.extend_from_slice(&[0x50, 0x4B, 0x03, 0x04]); // signature
|
|
zip.extend_from_slice(&[0x0A, 0x00]); // version needed
|
|
zip.extend_from_slice(&[0x00, 0x00]); // flags
|
|
zip.extend_from_slice(&[0x00, 0x00]); // compression: store
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // mod time/date
|
|
zip.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
|
|
zip.extend_from_slice(&(small_body.len() as u32).to_le_bytes()); // compressed size (actual)
|
|
zip.extend_from_slice(&oversized_claim.to_le_bytes()); // uncompressed size (forged)
|
|
zip.extend_from_slice(&8u16.to_le_bytes()); // filename length
|
|
zip.extend_from_slice(&0u16.to_le_bytes()); // extra field length
|
|
zip.extend_from_slice(b"SKILL.md");
|
|
zip.extend_from_slice(small_body);
|
|
|
|
let err = super::extract_skill_from_zip(&zip).unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("too large"),
|
|
"Oversized entry should be rejected, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
// ── SSRF prevention regression tests ────────────────────────────────
|
|
|
|
#[test]
|
|
fn test_is_private_ip_blocks_loopback() {
|
|
let loopback: std::net::IpAddr = "127.0.0.1".parse().unwrap();
|
|
// is_private_ip checks v4.is_private() which does NOT include loopback,
|
|
// but validate_fetch_url checks is_loopback() separately. Test the full flow.
|
|
assert!(loopback.is_loopback());
|
|
// Also verify via validate_fetch_url
|
|
assert!(super::validate_fetch_url("https://127.0.0.1/skill.md").is_err());
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_private_ip_blocks_private_ranges() {
|
|
let cases: Vec<(&str, bool)> = vec![
|
|
("10.0.0.1", true),
|
|
("10.255.255.255", true),
|
|
("172.16.0.1", true),
|
|
("172.31.255.255", true),
|
|
("192.168.1.1", true),
|
|
("192.168.0.0", true),
|
|
];
|
|
for (ip_str, expect_private) in cases {
|
|
let ip: std::net::IpAddr = ip_str.parse().unwrap();
|
|
assert_eq!(
|
|
super::is_private_ip(&ip),
|
|
expect_private,
|
|
"Expected is_private_ip({}) = {}",
|
|
ip_str,
|
|
expect_private
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_private_ip_blocks_link_local() {
|
|
// 169.254.0.0/16 range (link-local)
|
|
let cases = vec!["169.254.1.1", "169.254.0.1", "169.254.255.255"];
|
|
for ip_str in cases {
|
|
let ip: std::net::IpAddr = ip_str.parse().unwrap();
|
|
// is_private_ip includes v4.is_link_local()
|
|
assert!(
|
|
super::is_private_ip(&ip),
|
|
"Expected is_private_ip({}) = true (link-local)",
|
|
ip_str
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_private_ip_allows_public() {
|
|
let public_ips = vec!["8.8.8.8", "1.1.1.1", "93.184.216.34", "151.101.1.67"];
|
|
for ip_str in public_ips {
|
|
let ip: std::net::IpAddr = ip_str.parse().unwrap();
|
|
assert!(
|
|
!super::is_private_ip(&ip),
|
|
"Expected is_private_ip({}) = false (public IP)",
|
|
ip_str
|
|
);
|
|
assert!(!ip.is_loopback(), "Expected {} is not loopback", ip_str);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_private_ip_blocks_ipv4_mapped_ipv6() {
|
|
// Test the IPv4-mapped unwrapping logic end-to-end through
|
|
// validate_fetch_url. IPv6 URLs like https://[::ffff:127.0.0.1]/path
|
|
// must be correctly detected as private/loopback.
|
|
|
|
// ::ffff:127.0.0.1 mapped -> 127.0.0.1 (loopback) -- must be blocked
|
|
let err = super::validate_fetch_url("https://[::ffff:127.0.0.1]/skill.md").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("private") || err.to_string().contains("loopback"),
|
|
"IPv4-mapped loopback should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// ::ffff:192.168.1.1 mapped -> 192.168.1.1 (private) -- must be blocked
|
|
let err = super::validate_fetch_url("https://[::ffff:192.168.1.1]/skill.md").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("private") || err.to_string().contains("loopback"),
|
|
"IPv4-mapped private should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// ::ffff:10.0.0.1 mapped -> 10.0.0.1 (private) -- must be blocked
|
|
let err = super::validate_fetch_url("https://[::ffff:10.0.0.1]/skill.md").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("private") || err.to_string().contains("loopback"),
|
|
"IPv4-mapped 10.x should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// ::ffff:8.8.8.8 mapped -> 8.8.8.8 (public) -- must be allowed
|
|
assert!(
|
|
super::validate_fetch_url("https://[::ffff:8.8.8.8]/skill.md").is_ok(),
|
|
"IPv4-mapped public IP should be allowed"
|
|
);
|
|
|
|
// Pure IPv6 loopback ::1 -- must be blocked
|
|
let err = super::validate_fetch_url("https://[::1]/skill.md").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("private") || err.to_string().contains("loopback"),
|
|
"IPv6 loopback should be blocked, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_restricted_host_blocks_metadata() {
|
|
// Cloud metadata endpoint (AWS/GCP/Azure style)
|
|
let err =
|
|
super::validate_fetch_url("https://169.254.169.254/latest/meta-data/").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("private") || err.to_string().contains("link-local"),
|
|
"Metadata IP should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// GCP metadata hostname
|
|
let err =
|
|
super::validate_fetch_url("https://metadata.google.internal/something").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("internal hostname"),
|
|
"metadata.google.internal should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// Generic .internal domain
|
|
let err = super::validate_fetch_url("https://service.internal/api").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("internal hostname"),
|
|
".internal domains should be blocked, got: {}",
|
|
err
|
|
);
|
|
|
|
// .local domain
|
|
let err = super::validate_fetch_url("https://myhost.local/skill.md").unwrap_err();
|
|
assert!(
|
|
err.to_string().contains("internal hostname"),
|
|
".local domains should be blocked, got: {}",
|
|
err
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn test_is_restricted_host_allows_normal() {
|
|
let allowed = vec![
|
|
"https://github.com/repo/SKILL.md",
|
|
"https://clawhub.dev/api/v1/download?slug=foo",
|
|
"https://raw.githubusercontent.com/user/repo/main/SKILL.md",
|
|
"https://example.com/skills/deploy.md",
|
|
];
|
|
for url in allowed {
|
|
assert!(
|
|
super::validate_fetch_url(url).is_ok(),
|
|
"Expected validate_fetch_url({}) to succeed",
|
|
url
|
|
);
|
|
}
|
|
}
|
|
|
|
#[test]
|
|
fn test_empty_url_param_is_treated_as_absent() {
|
|
// LLMs sometimes pass "" for optional parameters instead of omitting them.
|
|
// Before the fix, url: "" would match Some("") and attempt to fetch from an
|
|
// empty URL (failing with an invalid URL error) instead of falling through to
|
|
// the catalog lookup. The full execute path cannot be tested here without a
|
|
// real catalog and database, so this test verifies the parameter filtering
|
|
// behaviour directly.
|
|
let params = serde_json::json!({"name": "my-skill", "url": ""});
|
|
let url = params
|
|
.get("url")
|
|
.and_then(|v| v.as_str())
|
|
.filter(|s| !s.is_empty());
|
|
assert!(
|
|
url.is_none(),
|
|
"empty url string should be treated as absent"
|
|
);
|
|
}
|
|
}
|