pr-create
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill demonstrates high security awareness by implementing explicit 'Hard rules' to prevent dangerous actions.- [DATA_EXPOSURE]: Includes a mandatory 'Sensitive-file scan' in Step 2 that checks for files like .env, credentials, .pem, and private keys, blocking the PR creation if these are detected in the diff to prevent accidental data leaks.- [COMMAND_EXECUTION]: Employs standard git and gh (GitHub CLI) commands for branch management and PR creation. It properly uses shell heredocs to handle multi-line input safely during PR creation.- [PROMPT_INJECTION]: While the skill ingests external data (commit messages and PR templates) that could theoretically contain indirect prompt injections (Category 8), the risk is mitigated by the requirement for explicit user approval (Step 4) before any action is taken.
Audit Metadata