clarify
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions.
- [SAFE]: The skill uses a "critique-first" approach for file modifications, requiring an explicit "apply" command from the user, which serves as a human-in-the-loop security control.
- [SAFE]: Indirect Prompt Injection Surface:
- Ingestion points: User-provided UI text and frontend code (SKILL.md).
- Boundary markers: The skill does not define specific delimiters for input data.
- Capability inventory: File modification (SKILL.md).
- Sanitization: No explicit sanitization of input text is defined.
- Note: The inherent risk of processing untrusted UI code is mitigated by the requirement for manual user approval before writing changes.
Audit Metadata