evp-craft
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-provided inputs like ICP definitions and pain points to construct marketing copy. This creates an attack surface for indirect prompt injection where malicious instructions embedded in the processed data could attempt to override agent behavior.
Audit Metadata