code-reviewer

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard development tools including git, gh (GitHub CLI), and npm. These are used appropriately for checking out branches, viewing pull requests, and running project-specific preflight checks (npm run preflight).
  • [EXTERNAL_DOWNLOADS]: The skill interacts with GitHub to fetch pull request data and checkout remote branches. This is the intended primary purpose of a code review tool and targets a well-known service.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read PR descriptions, comments, and code diffs. While this introduces a surface where untrusted content from a repository could attempt to influence the agent's behavior, the skill's structure provides clear pillars and checklists to maintain a structured review process.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 09:13 PM
Security Audit — agent-trust-hub — code-reviewer