business-plan

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content (project ideas and draft materials) to generate a business plan.
  • Ingestion points: User-provided project ideas and half-finished materials in the initial prompt or subsequent interactions.
  • Boundary markers: Absent; the instructions do not explicitly define markers to separate user data from instructions.
  • Capability inventory: The skill uses web search for market research and document generation tools to create Word files.
  • Sanitization: No explicit instructions are provided for sanitizing or escaping user-provided input before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 02:01 PM