resolve-pr-comments
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/fetch-pr-data.shto retrieve pull request data. This script utilizes the GitHub CLI (gh) to perform GraphQL queries and handle pagination for reviews, threads, and commits.\n- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to the ingestion and processing of untrusted external content.\n - Ingestion points: Review comments, review bodies, and commit messages are fetched from GitHub via the
fetch-pr-data.shscript (Step 1).\n - Boundary markers: The instructions do not define clear delimiters or use specialized prompts to isolate the untrusted PR content from the agent's logic.\n
- Capability inventory: The skill orchestrates the
/resolve-findingsskill (Step 7) which modifies the codebase and the/reply-to-pr-threadsskill (Step 10) which posts messages back to GitHub.\n - Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested text before it is used to influence the agent's actions.
Audit Metadata