Skill audit report
>-
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
104 GitHub stars
Stars/forks activity
WARN57
104 stars, 18 forks; issue activity unavailable in current metadata
Recent maintenance
PASS88
2mo since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
INFO70
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
WARN54
credential or environment access, external package install surface
Install availability
PASS92
npx skills add harness/harness-skills --skill create-sbom
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN46
secrets or environment access, filesystem or document access
Repository evidence
PASS86
https://github.com/harness/harness-skills/tree/main/skills/create-sbom
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add harness/harness-skills --skill create-sbom
Repository
88
https://github.com/harness/harness-skills/tree/main/skills/create-sbom
License
86
Apache-2.0
Maintenance
88
2mo since push
AI review
55
No critical security issues found. The skill avoids executing pipelines and requires user confirmation before writes.
README/SKILL.md completeness
84
Usable description available
Dependency risk
54
credential or environment access, external package install surface
Install command safety
92
standard package or runtime install path
Permission surface
46
secrets or environment access, filesystem or document access
Stars/forks activity
57
104 stars, 18 forks; issue activity unavailable in current metadata
Adoption
68
104 GitHub stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
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