pull-request-feedback-loop
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches external, potentially untrusted data from GitHub Pull Request comments and review threads.
- Ingestion points: The skill fetches review context in
SKILL.md(Step 2) usinggh pr view --commentsandgh api. - Boundary markers: The instructions do not specify any delimiters or safety markers to help the agent distinguish between legitimate feedback and malicious instructions embedded in comments.
- Capability inventory: The agent is instructed to edit files (Step 4) and execute local tests or checks (Step 5) based on the gathered feedback, providing an execution path for injected instructions.
- Sanitization: No sanitization, validation, or filtering of the fetched comment content is mentioned in the process.
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) and project-specific test suites to perform its tasks. - Evidence: The skill explicitly calls for running
gh pr status,gh pr view,gh api, and various local test commands as part of the PR feedback loop workflow.
Audit Metadata