Skill audit report
Create, repair or reuse an agent evaluation from agreed behaviors and scoring; validate sensitivity, independently review, freeze and prepare eval-only delivery.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
FAIL30
20 GitHub stars
Stars/forks activity
FAIL32
20 stars, 1 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
16d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO72
command execution surface
Install availability
PASS92
npx skills add agentagon/agentagon --skill eval
Install command safety
INFO68
dynamic command execution, standard package or runtime install path
Permission surface
INFO62
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/agentagon/agentagon/tree/main/skills/eval
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add agentagon/agentagon --skill eval
Repository
88
https://github.com/agentagon/agentagon/tree/main/skills/eval
License
86
Apache-2.0
Maintenance
100
16d since push
AI review
55
The skill instructs running an external telemetry command at workflow start; this should be clearly opt-in and must not transmit repository contents, environment secrets, or user data beyond the declared metadata.
README/SKILL.md completeness
86
Usable description available
Dependency risk
72
command execution surface
Install command safety
68
dynamic command execution, standard package or runtime install path
Permission surface
62
shell or command execution, filesystem or document access
Stars/forks activity
32
20 stars, 1 forks; issue activity unavailable in current metadata
Adoption
42
20 GitHub stars
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.
Compare nearby options