refund-page-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of structured markdown instructions providing legal and business guidance for policy generation. No malicious code or dangerous commands were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection risks. While it processes user-provided business context (product category, jurisdiction, refund model), it lacks the exploitable capabilities necessary to form a functional attack surface. 1. Ingestion points: User-provided business details and jurisdiction settings in the conversation context. 2. Boundary markers: Absent. 3. Capability inventory: None (no tool usage, network access, or file system modifications are requested or used). 4. Sanitization: Absent.
Audit Metadata