code-review

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes standard Git tools (git diff, git log, git rev-parse) and the GitHub CLI (gh) to retrieve repository state. It also references a vendor-specific command /setup-ouyangjiahong-skills for environment setup.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret external text from PR descriptions and issue trackers which could contain malicious instructions.
  • Ingestion points: Pull Request descriptions and issue data retrieved via docs/agents/issue-tracker.md.
  • Boundary markers: The skill does not define specific delimiters or security instructions to prevent the agent from following commands embedded in external descriptions.
  • Capability inventory: Access to shell commands (git/gh) and repository file reading.
  • Sanitization: No sanitization of the external content is performed before processing.
  • [EXTERNAL_DOWNLOADS]: The skill fetches metadata and text from external PR and issue tracking platforms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 02:04 AM
Security Audit — agent-trust-hub — code-review