consult-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data to generate structured documents, creating an attack surface for indirect prompt injection.
- Ingestion points: User-provided business ideas, target markets, and current situations defined in the workflow (SKILL.md).
- Boundary markers: The instructions lack delimiters or warnings to ignore instructions embedded within the user's business data.
- Capability inventory: The skill produces markdown content that is automatically passed to downstream agents for PPTX conversion (moai-officer:doc-pptx) and linguistic refinement (moai-writer:korean-humanize).
- Sanitization: There are no documented steps for escaping or validating user-provided strings before they are interpolated into the final output.
Audit Metadata