flowhunt-skill
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided responses to identify workflow patterns, creating a potential surface for indirect prompt injection via the intake questionnaire.
- Ingestion points: User answers to the five-question intake survey in SKILL.md.
- Boundary markers: None defined; instructions do not use delimiters for user-provided data.
- Capability inventory: None; the skill provides informational output only and does not execute commands, access the network, or write files.
- Sanitization: No input validation or escaping mechanisms are specified.
Audit Metadata