Skill audit report
ap-fresh-verifier Audit report.
L4 blind fresh verifier - independently checks a candidate roadmap or plan against the exact mission and repository; APPROVE/REJECT, default-FAIL.
OpenAgentSkill Trust Score
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
988 GitHub stars
Stars/forks activity
INFO71
988 stars, 66 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
2mo since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
INFO72
command execution surface
Install availability
PASS92
npx skills add Spielewoy/autoprompt-skill --skill ap-fresh-verifier
Install command safety
PASS92
standard package or runtime install path
Permission surface
INFO62
shell or command execution, filesystem or document access
Repository evidence
PASS86
https://github.com/Spielewoy/autoprompt-skill/tree/main/agents/reasonix/skills/ap-fresh-verifier
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install and adoption review
Install path
92
npx skills add Spielewoy/autoprompt-skill --skill ap-fresh-verifier
Repository
88
https://github.com/Spielewoy/autoprompt-skill/tree/main/agents/reasonix/skills/ap-fresh-verifier
License
86
MIT
Maintenance
88
2mo since push
AI review
55
SKILL.md references activation-scoped persona files, MISSION POINTER, and PROMPTS.txt without specifying how those paths are resolved, which can make execution ambiguous outside the Autoprompt harness.
README/SKILL.md completeness
84
Usable description available
Dependency risk
72
command execution surface
Install command safety
92
standard package or runtime install path
Permission surface
62
shell or command execution, filesystem or document access
Stars/forks activity
71
988 stars, 66 forks; issue activity unavailable in current metadata
Adoption
88
988 GitHub stars
Warnings
- SKILL.md references activation-scoped persona files, MISSION POINTER, and PROMPTS.txt without specifying how those paths are resolved, which can make execution ambiguous outside the Autoprompt harness.
- The skill says it is terminal and does not spawn agents, but also includes an 'If you spawn' clause; this contradiction should be resolved to prevent confusion or misuse.
- No explicit guardrail against exfiltration of repository contents or prompt/ledger data, though the existing constraints reduce practical risk.
- Quality score needs review
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