pr-qa
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and acts upon external data from pull request comments and local repository documentation without sanitization or explicit boundary markers.
- Ingestion points: Retrieves pull request comments via the GitHub API and scans the repository for architectural documentation (e.g., ARCHITECTURE.md, README.md).
- Boundary markers: None identified; the agent is instructed to directly incorporate findings from these external sources into code fixes or responses.
- Capability inventory: Includes the ability to push code, modify pull requests, and execute commands using the GitHub CLI and security audit tools.
- Sanitization: None identified.
- [EXTERNAL_DOWNLOADS]: The skill suggests installing the well-known security utility gitleaks via standard package managers (npm, pnpm, bun, or brew) if the tool is missing from the environment.
- [COMMAND_EXECUTION]: The workflow executes automated repository management and security auditing tasks using git, the GitHub CLI (gh), and several ecosystem-specific dependency auditors such as npm audit and pip audit.
Audit Metadata