Skill audit report

oma-explanation Audit report.

Turn a code change (diff, PR, branch, commit range) into a rich, self-contained interactive HTML explainer with Background / Intuition / Code / Quiz sections. Use for explain, walkthrough, code-change explanation, diff/PR/branch explainer requests — 설명서, 해설, コード解説, 代码讲解. Produces a single offline-capable HTML file with diagrams, callouts, and an accessible quiz.

BLOCKED · BLOCKNeeds reviewGenerated Oct 21, 2026Heuristic metadata audit
75
Audit
67
Trust
74
Quality
72
Security
88
Maintain
92
Install

OpenAgentSkill Trust Score

67
Manual review

OpenAgentSkill Trust Score

The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

86

1.3K GitHub stars

Stars/forks activity

INFO

77

1.3K stars, 146 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

88

2mo since push

License clarity

PASS

86

MIT

README/SKILL.md completeness

PASS

86

Metadata includes enough usage and workflow context

Dependency/runtime risk

WARN

46

command execution surface, credential or environment access

Install availability

PASS

92

npx skills add first-fluke/oh-my-agent --skill oma-explanation

Install command safety

PASS

92

standard package or runtime install path

Permission surface

FAIL

22

secrets or environment access, shell or command execution

Repository evidence

PASS

86

https://github.com/first-fluke/oh-my-agent/tree/main/.agents/skills/oma-explanation

Review status

INFO

66

AI review data available

Agent Proven outcomes

INFO

54

No agent outcome data yet

Checks

Install and adoption review

7 Passed · 13 Needs review

Install path

92

PASS

npx skills add first-fluke/oh-my-agent --skill oma-explanation

Repository

88

PASS

https://github.com/first-fluke/oh-my-agent/tree/main/.agents/skills/oma-explanation

License

86

PASS

MIT

Maintenance

88

PASS

2mo since push

AI review

55

CHECK

SKILL.md does not explicitly require HTML-escaping all diff-derived content and PR text before embedding it in the generated explainer; this should be codified in the html-contract to prevent script/HTML injection inside the self-contained file.

README/SKILL.md completeness

86

PASS

Usable description available

Dependency risk

46

FIX

command execution surface, credential or environment access

Install command safety

92

PASS

standard package or runtime install path

Permission surface

22

FIX

secrets or environment access, shell or command execution

Stars/forks activity

77

CHECK

1.3K stars, 146 forks; issue activity unavailable in current metadata

Adoption

88

PASS

1.3K GitHub stars

Warnings

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • SKILL.md does not explicitly require HTML-escaping all diff-derived content and PR text before embedding it in the generated explainer; this should be codified in the html-contract to prevent script/HTML injection inside the self-contained file.
  • The `open <path>` step should be specified to use an argument-list subprocess call rather than shell interpolation, so a malicious or unexpected slug/path cannot inject shell commands.
  • The excerpt does not include a dedicated setup/installation section; listing required tools (`git`, optional `gh`, optional Serena MCP) and their installation state would make the skill more self-contained.
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Dependency/runtime risk: command execution surface, credential or environment access
  • 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

Related skills to audit next