open-pr-agentic
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to read pull request templates from the repository (e.g., .github/pull_request_template.md) and is explicitly instructed to follow instructions contained within HTML comments in those files. This creates a surface for indirect prompt injection where a malicious repository could influence the agent's behavior.
- Ingestion points: Repository template files.
- Boundary markers: None; the agent is explicitly told to treat embedded HTML comments as instructions.
- Capability inventory: Reading local files and creating pull requests via the GitHub CLI tool.
- Sanitization: No sanitization or validation of the template content is performed before processing.
Audit Metadata