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.mdfiles (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 commentto 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
ghCLI tool for GitHub interactions. This is standard behavior for interacting with a well-known service and does not escalate severity.
Audit Metadata