penetration-tester
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a mechanism to retrieve its operational scope and rules of engagement from an external source, creating a potential vector for indirect prompt injection.\n
- Ingestion points: Data is ingested via the
get_pentest_contextquery process inSKILL.md.\n - Boundary markers: No delimiters or safety instructions are provided to help the agent distinguish between its core instructions and the external context data.\n
- Capability inventory: The skill encourages the agent to perform high-risk security operations including exploit validation, payload development, and identifying persistence mechanisms.\n
- Sanitization: The skill lacks any description of validation or sanitization protocols for the retrieved testing parameters.
Audit Metadata