pull-request
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull request comments, which presents a surface for indirect prompt injection. Ingestion points: External comments are fetched via scripts/gh-review-comments during the resolve and reply workflows. Boundary markers: None are explicitly defined in the instructions for the interpolation of comment text into the agent's context. Capability inventory: The agent has access to git for committing and pushing code changes, and gh for GitHub API mutations. Sanitization: No specific sanitization or filtering is described for the content of external comments before processing.
- [COMMAND_EXECUTION]: The skill utilizes the git, gh, and jq command-line tools to interact with the local repository and the GitHub API. These operations include creating branches, pushing commits, and managing pull requests, which align with the skill's stated purpose and user-initiated workflows.
Audit Metadata