conventional-pull-requests
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Command Execution] (SAFE): The skill performs shell commands using
gitandghto inspect repository state, push branches, and create pull requests. These operations are consistent with the tool's primary purpose. - [Indirect Prompt Injection] (LOW): The skill ingests untrusted repository content which could contain malicious instructions designed to manipulate the PR creation process.
- Ingestion points:
git log,git diff, and PR template files in the.github/directory. - Boundary markers: None. The agent treats all ingested text as data without explicit markers to ignore embedded instructions.
- Capability inventory: The agent can execute
git pushandgh pr createusing generated arguments for titles and bodies. - Sanitization: No sanitization is performed on the data retrieved from the repository before it is used to draft the PR.
Audit Metadata