make-pr-easy-to-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Pull Requests, including diffs, commit messages, and descriptions. Maliciously crafted content in a PR could attempt to influence the agent's actions during the cleanup process.\n
- Ingestion points: Pull request content accessed via
gh pr viewandgit fetchinSKILL.md.\n - Boundary markers: Not explicitly defined in the workflow instructions.\n
- Capability inventory: Uses
gitandghfor history manipulation and PR metadata inspection.\n - Sanitization: The skill includes verification steps (comparing tree hashes) to ensure behavior is preserved, which serves as a manual integrity check.\n- [COMMAND_EXECUTION]: The skill utilizes standard
gitandghcommands to perform its primary functions of PR inspection and history cleanup. These are expected capabilities for a developer tool and do not involve unauthorized privilege escalation.
Audit Metadata