git-pr
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- Metadata (SAFE): The skill name, description, and workflow are consistent and legitimate for the stated purpose of PR management.
- Indirect Prompt Injection (LOW): The skill is designed to process untrusted data (branch changes) to generate summaries. This creates an attack surface where malicious code in a PR could attempt to influence the agent's summary or PR description. However, as no implementation code is provided, there is no direct risk of command execution or exfiltration.
- Code Execution (SAFE): No scripts (Python, Node.js, Shell) or binaries are included with this skill. It relies entirely on natural language instructions.
Audit Metadata