antislop-code
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional content focused on improving code comment hygiene.
- [SAFE]: Includes a strict scope guardrail in SKILL.md that prohibits the agent from modifying executable code, logic, or control flow, ensuring that changes are restricted to non-functional comments.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external code files via Read, Glob, and Grep tools. While it lacks explicit boundary markers or sanitization for untrusted data, the instructions are specifically designed to filter out and remove common AI-generated patterns and restrict editing to comments only. Ingestion points: code files; Boundary markers: absent; Capability inventory: Read, Write, Edit, Glob, Grep; Sanitization: absent.
Audit Metadata