Skill audit report
Use when the user wants to adversarially stress-test a guardrail, classifier, prompt, or API they own or are authorized to test, to surface the distinct ways it fails. Generates adversarial inputs, runs them through the target and a ground-truth oracle, logs every target-vs-oracle disagreement as a failure de-duplicated by technique class, and loops until rounds stop surfacing new classes. Produces a catalogue of distinct, reproducible failures — the attacker half of a find→fix setup. Not for patching the target, and not for attacking systems the user does not own or have permission to test.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
163 GitHub stars
Stars/forks activity
WARN57
163 stars, 19 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
2mo since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO64
credential or environment access, network or browser surface
Install availability
PASS92
npx skills add gaasher/Agent-Loop-Skills --skill red-team
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN60
secrets or environment access, network or browser access
Repository evidence
PASS86
https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/red-team
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add gaasher/Agent-Loop-Skills --skill red-team
Repository
88
https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/red-team
License
86
MIT
Maintenance
88
2mo since push
AI review
55
The SKILL.md excerpt is truncated at the 'Labeling classes' section, but the repository likely contains the full content; no critical issues found.
README/SKILL.md completeness
86
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Usable description available
Dependency risk
64
credential or environment access, network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
60
secrets or environment access, network or browser access
Stars/forks activity
57
163 stars, 19 forks; issue activity unavailable in current metadata
Adoption
68
163 GitHub stars