wardley
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external business context provided by users, which serves as an ingestion point for potentially untrusted data.\n
- Ingestion points: User-provided business context and needs during interactive mapping sessions (SKILL.md).\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the business data and potential embedded commands.\n
- Capability inventory: The skill requests access to tools including
Bash,Read,Write,Edit, andAgent(SKILL.md).\n - Sanitization: No evidence of input sanitization, validation, or escaping of the user-provided context is present in the instructions.
Audit Metadata