reviewing-code

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from external repositories to inform its reviews.\n
  • Ingestion points: The agent reads pull request diffs, repository history, and CLAUDE.md files (Steps 2, 3, 4, 6).\n
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted repository content from the agent's instructions.\n
  • Capability inventory: The skill uses gh pr comment to write feedback to GitHub and executes multiple parallel agents.\n
  • Sanitization: The skill lacks automated sanitization or filtering for the external code and documentation it ingests.\n- [COMMAND_EXECUTION]: The skill uses the gh CLI tool for GitHub interactions. This is standard behavior for interacting with a well-known service and does not escalate severity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 08:32 AM
Security Audit — agent-trust-hub — reviewing-code