super-good-pr
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process untrusted external data (git diffs and commit messages), creating a surface for indirect prompt injection.
- Ingestion points: The agent ingests commit history, diffs, and existing pull request metadata from the local environment.
- Boundary markers: The instructions do not define explicit delimiters or instructions to isolate untrusted diff content from the core instructions.
- Capability inventory: The skill encourages the use of shell-based CLI tools (
git,gh) to read and update repository data. - Sanitization: While the skill provides advice on avoiding shell injection via CLI flags, it does not include instructions for sanitizing or escaping the content of the diffs themselves before they are processed by the agent.
- [COMMAND_EXECUTION]: The skill references standard development tools such as
git,gh,cargo, andpnpm. It promotes secure practices by advising the use of file-based arguments (e.g.,--body-file) for the GitHub CLI to mitigate shell injection vulnerabilities when handling potentially malicious content in PR bodies.
Audit Metadata