gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-09-03 10:09:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add skill system for shareable prompt-level agent behaviors

Browse Source 
Skills are TOML manifests containing instructions injected into the LLM
context. They can be loaded from GitHub repos, URLs, or local files and
activated via /skill commands or custom slash commands from any channel.

Five defense layers protect against malicious skills: static analysis
(Aho-Corasick + skill-specific regex), hard tool whitelist (registry +
execution level), resource restrictions (domains, workspace paths, tool
call budget), BLAKE3 approval pinning, and structural prompt isolation
via <external_skill> wrapper with reassertion block.

Co-Authored-By: Claude Opus 4.6 <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-02-06 08:51:50 -08:00
co-authored by Claude Opus 4.6
parent 48ab73574e
commit c19986f06d
12 changed files with 2558 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.toml
+1
View File
@@ -18,6 +18,7 @@ reqwest = { version = "0.12", default-features = false, features = ["json", "rus
# Serialization
serde = { version = "1", features = ["derive"] }
serde_json = "1"
toml = "0.8"
# Database
deadpool-postgres = "0.14"