flow-qa
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The agent reads external files including ticket.md, specifications, project plans, and existing review logs.
- Boundary markers: No explicit delimiters or boundary instructions are defined to separate ingested data from the agent's instructions.
- Capability inventory: The skill describes interacting with APIs, databases, and executing project-specific CLI tools like flow-build and flow-review.
- Sanitization: No specific content sanitization or validation logic is requested for the external inputs.
- [NO_CODE]: The skill consists entirely of markdown instructions and configuration metadata without any embedded executable scripts or binary files.
Audit Metadata