pr-description-generator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of Markdown-based templates and examples. It does not include any instructions designed to override AI safety or system prompts.
- [NO_CODE] (SAFE): No executable scripts (Python, Node.js, Shell), configuration files for package managers, or binary files are present in the skill.
- [DATA_EXFILTRATION] (SAFE): There are no network request commands (e.g., curl, wget) or file system access patterns that would indicate data exposure or exfiltration.
- [INDIRECT_PROMPT_INJECTION] (INFO): While the skill is designed to process untrusted data (code changes and PR context), it lacks the capabilities (write, execute, or network access) to be exploited; the severity remains at the INFO tier for display-only output.
Audit Metadata