create-pr
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain embedded instructions intended to manipulate the agent's output or behavior.
- Ingestion points: The skill reads commit messages, git diffs, and pull request templates from the local repository (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions found within the commit history or templates.
- Capability inventory: The agent is authorized to perform git operations (commit, push, merge) and use the
ghCLI tool to create and edit pull requests, including attaching local files. - Sanitization: There is no evidence of sanitization or filtering logic to prevent the agent from obeying instructions embedded in the analyzed code or documentation.
Audit Metadata