make-pr
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the local environment to generate instructions or content for external actions.
- Ingestion points: The agent is instructed to inspect commits and code diffs from the local repository (SKILL.md, Step 2).
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading git history.
- Capability inventory: The skill uses
git pushand interacts with GitHub APIs to create and update pull requests, including setting the title and body (SKILL.md, Steps 3-4). - Sanitization: The skill lacks explicit sanitization steps for commit messages or diff content before they are used to populate pull request fields.
Audit Metadata