create-pull-requests
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for Git operations, including branch management and pull request creation, which are standard for developer-oriented AI agents.
- [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by instructing the agent to ingest and summarize external data from commit messages and issue trackers.
- Ingestion points: SKILL.md (Scanning user requests, branch names, commit messages, and issue-tracker context).
- Boundary markers: None identified.
- Capability inventory: Branch pushing and pull request creation.
- Sanitization: None identified.
Audit Metadata