vuln-diagnose
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a guide for building deterministic proof-of-concepts for security testing. It promotes safe practices like using test accounts and ruling out false positives.
- [INDIRECT_PROMPT_INJECTION]: The skill describes processing external tool outputs which may be untrusted. 1. Ingestion points: Tool outputs and reports of suspected vulnerabilities mentioned in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The instructions suggest the use of network tools for HTTP requests and browser interactions for XSS testing. 4. Sanitization: No specific input validation or sanitization of external data is described.
Audit Metadata