skills/leek/agent-skills/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard git commands (git diff, git log, git rev-parse) to analyze code changes within the local repository.
  • [SAFE]: It implements a 'Standards' axis that applies established software engineering principles (Martin Fowler's code smells) to improve code quality without introducing external risks.
  • [SAFE]: The skill correctly identifies sensitive files like .env as places where secrets are managed and does not attempt to exfiltrate them or hardcode credentials.
  • [SAFE]: It utilizes project-local documentation (AGENTS.md, CONTRIBUTING.md, .cursor/rules) to define scope, maintaining the principle of least privilege by focusing on the repository's own context.
  • [SAFE]: The use of sub-agents is scoped to the execution of the code review briefs provided within the skill, with no evidence of prompt injection or attempt to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 12:39 AM
Security Audit — agent-trust-hub — code-review