kf-g-git-pr-red-green-stacked-pr
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the automated processing of untrusted data (user-provided bug descriptions and existing project code) to generate commits and pull requests.
- Ingestion points: The agent ingests external codebase content and user prompts to create reproduction tests (references/workflow.md).
- Boundary markers: There are no explicit instructions or delimiters to help the agent distinguish between its system instructions and potential injection attempts embedded in the code or comments it processes.
- Capability inventory: The skill uses file system access to modify code and utilizes the GitHub CLI (
gh stack) to create, submit, and merge pull requests (references/workflow.md). - Sanitization: No sanitization or escaping mechanisms are specified for content extracted from the codebase that is subsequently used in PR descriptions or commit messages.
Audit Metadata