Skill audit report
hermes-update-doctor Audit report.
Use when stuck, contradictory, blocked, or incomplete Hermes updates must be diagnosed across Git state, remotes, running processes, caches, and installed versions before recovery.
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
INFO62
126 GitHub stars
Stars/forks activity
WARN57
126 stars, 11 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
30d since push
License clarity
PASS86
Apache-2.0
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
INFO72
credential or environment access
Install availability
PASS92
npx skills add asimons81/hermes-field-kit --skill hermes-update-doctor
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL36
secrets or environment access, shell or command execution
Repository evidence
PASS86
https://github.com/asimons81/hermes-field-kit/tree/main/skills/hermes-update-doctor
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 asimons81/hermes-field-kit --skill hermes-update-doctor
Repository
88
https://github.com/asimons81/hermes-field-kit/tree/main/skills/hermes-update-doctor
License
86
Apache-2.0
Maintenance
100
30d since push
AI review
55
SKILL.md is strong on safety and workflow but light on concrete read-only diagnostic commands; the referenced protocol.md does not actually provide expanded command-level guidance, only restates the same phase headings.
README/SKILL.md completeness
86
Usable description available
Dependency risk
72
credential or environment access
Install command safety
92
standard package or runtime install path
Permission surface
36
secrets or environment access, shell or command execution
Stars/forks activity
57
126 stars, 11 forks; issue activity unavailable in current metadata
Adoption
68
126 GitHub stars
Warnings
- Permission surface may require sandboxing
- SKILL.md is strong on safety and workflow but light on concrete read-only diagnostic commands; the referenced protocol.md does not actually provide expanded command-level guidance, only restates the same phase headings.
- The skill lists linux, macos, and windows platforms but does not include OS-specific command examples or differences for process inspection, package metadata, or path resolution.
- No explicit validation criteria are given for confirming that the 'actual running code path' was verified, even though this is listed as a safety requirement.
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- Stars/forks activity: 126 stars, 11 forks; issue activity unavailable in current metadata
- Permission surface: secrets or environment access, shell or command execution
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