customer-support
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- Indirect Prompt Injection (INFO): The skill processes untrusted customer inquiries as part of its support workflow. While no specific boundary markers are defined for this input, the risk is negligible because the skill lacks any capabilities (such as code execution, file modification, or network requests) to be exploited. 1. Ingestion points: Customer inquiry and context fields in SKILL.md. 2. Boundary markers: None specified. 3. Capability inventory: No tools or scripts available. 4. Sanitization: None provided.
- General (SAFE): No malicious instructions, obfuscation, or hardcoded credentials were found in the skill metadata or instructional content.
Audit Metadata