pr
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates pull request management by providing structured templates and commands for standard development workflows. It uses well-known command-line interfaces (git, gh, tea) and does not exhibit any malicious behaviors such as credential exfiltration, remote code execution, or obfuscation.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data from git history, which is a common requirement for generating pull request summaries.
- Ingestion points: Data enters the context via git diff and git log commands in SKILL.md and pr-creation.md to analyze changes and commit history.
- Boundary markers: The skill suggests using markdown templates to organize information, though it does not provide specific instructions to the agent to ignore potentially malicious instructions embedded in commit messages.
- Capability inventory: The agent is authorized to use git, gh, and tea commands to read repository state and create pull requests.
- Sanitization: No explicit filtering or sanitization of commit messages or diff content is performed before interpolation into the PR templates.
Audit Metadata