pr
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the
gitandgh(GitHub CLI) tools to inspect local changes, commit code, and push to remote repositories. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted repository data into pull request descriptions.
- Ingestion points: Repository metadata and code changes are read via
git statusandgit diff(SKILL.md). - Boundary markers: No explicit delimiters are used to wrap the repository content before processing.
- Capability inventory: Includes the ability to commit changes, push to remote servers, and create pull requests via network-enabled tools.
- Sanitization: There is no automated sanitization for content ingested from the repository diffs, though the instructions explicitly warn the agent not to stage secrets.
Audit Metadata