fix-pr-reviews
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from GitHub PR comments and reviews, which are external sources that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Pull request review comments, top-level review bodies, and general PR comments are fetched via
gh api(SKILL.md). - Boundary markers: The skill instructions enforce a strict triage process where the agent must report findings to the user and wait for explicit approval before applying any fixes.
- Capability inventory: The skill has the ability to read and write files, execute GitHub API commands, and perform
git pushoperations. - Sanitization: No explicit sanitization or escaping of the comment content is defined before the agent evaluates it for triage.
- [COMMAND_EXECUTION]: The skill relies on shell commands to interact with the GitHub CLI and the local Git repository.
- Evidence: The skill utilizes
gh pr list,gh apifor multiple endpoints, andgit pushto manage the PR workflow (SKILL.md).
Audit Metadata