Skill audit report

Q audit report.

q - Run SQL directly on delimited files and multi-file sqlite databases

EXPERIMENTAL · REVIEWSafe to tryGenerated Jun 17, 2026Heuristic metadata audit
88
Audit
87
Trust
100
Quality
81
Security
76
Maintain
92
Install

OpenAgentSkill Trust Score

87
Production candidate

Stars, maintenance, license, docs, install safety, permission surface, and installability.

The Trust Score is OpenAgentSkill's adoption layer. It is designed to help an agent decide whether a skill is safe enough to shortlist before installation.

GitHub adoption

PASS

100

10K GitHub stars

Stars/forks activity

PASS

92

10K stars, 424 forks; issue activity unavailable in current metadata

Recent maintenance

INFO

76

4mo since push

License clarity

PASS

86

GPL-3.0

README/SKILL.md completeness

INFO

74

Public metadata needs stronger README/SKILL.md context

Dependency/runtime risk

INFO

64

command execution surface, database surface

Install availability

PASS

92

npx skills add harelba/q

Install command safety

PASS

92

standard package or runtime install path

Permission surface

WARN

50

shell or command execution, filesystem or document access

Repository evidence

PASS

86

https://github.com/harelba/q

Review status

PASS

88

AI review data available

Checks

Install and adoption review

8 passed · 6 review

Install path

92

PASS

npx skills add harelba/q

Repository

88

PASS

https://github.com/harelba/q

License

86

PASS

GPL-3.0

Maintenance

76

CHECK

4mo since push

AI review

88

PASS

Approved with no listed issues

README/SKILL.md completeness

84

PASS

Usable description available

Dependency risk

64

CHECK

command execution surface, database surface

Install command safety

92

PASS

standard package or runtime install path

Permission surface

50

FIX

shell or command execution, filesystem or document access

Stars/forks activity

92

PASS

10K stars, 424 forks; issue activity unavailable in current metadata

Adoption

88

PASS

10K GitHub stars

Warnings

  • Permission surface may require sandboxing
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Permission surface: shell or command execution, filesystem or document access

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