pr-submit
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local
gitcommands (status,diff,log,push) andgh(GitHub CLI) to manage repository state and submit pull requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's diffs and commit history during the commit and review process.
- Ingestion points: Git diff outputs, file contents, and commit messages are read by the agent to determine commit structure and branch names.
- Boundary markers: No explicit delimiters or instructions are used to separate repository content from the skill's operational instructions.
- Capability inventory: The skill has the ability to commit changes, create new branches, and push code to remote repositories.
- Sanitization: No evidence of sanitization or filtering for the processed repository data is present.
Audit Metadata