skill-firewall
Security scanner for AI agent skills (SKILL.md packs). Use before installing any skill from ClawHub, GitHub or external sources, when auditing a skill directory for malicious patterns (prompt injection, credential theft, exfiltration, destructive commands, obfuscated payloads, persistence), or when
as observed 2026-11-16T00:36:19.090Z- Identifier
skill-firewall- Source
- ClawHub
- Version observed
- 1.0.5
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-11-14T23:38:46.955Z
- Observations recorded
- 2
- Installs (reported upstream)
- 2
- Weekly downloads (upstream)
- 74
- Declared license
- MIT-0
Observation history
2026-11-16T00:36:19.090Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Remove filename heuristics and all filename wording; reword docs to avoid trigger phrases (no unresolved local paths). Harness unchanged and green (18/18, 0 FP, strict-default che | "Docs: ClawHub install command and related skills (undo-first, vibecheck, vibegit). Strict-default behavior unchanged; 30 rules; harness 18/18, 0 FP." |
latestVersion |
"1.0.4" | "1.0.5" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.