business-evaluation
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that processes untrusted data, creating a surface for indirect prompt injection.
- Ingestion points: The skill captures business ideas from user input (Step 1) and market data from external analysis (Step 2).
- Boundary markers: Although the skill enforces structured output via
.claude/templates/business-evaluation-template.mdand requires evidence gating, it lacks explicit delimiters or instructions to the model to ignore embedded commands within the input data. - Capability inventory: The skill has the capability to write files to the
docs/andplans/reports/directories and can authorize the use of thespawn_agenttool for subtasks. - Sanitization: There are no instructions for sanitizing, escaping, or validating the input data before it is interpolated into analysis prompts.
Audit Metadata