business-evaluation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external market analysis data and user-provided business ideas, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill reads market research from
{plan-dir}/research/market-analysis.mdand accepts business idea descriptions from user prompts (SKILL.md). - Boundary markers: The skill does not define specific delimiters or explicit "ignore" instructions for the ingested content to prevent it from being interpreted as instructions.
- Capability inventory: The skill utilizes
spawn_agentfor sub-tasks and performs file read/write operations within the project workspace (SKILL.md). - Sanitization: No explicit content sanitization, validation, or escaping logic is defined for the imported market data or user input.
Audit Metadata