startup-idea-evaluator
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided startup ideas and business concepts, which are untrusted data sources.
- Ingestion points: User input in the form of startup descriptions and pitches.
- Boundary markers: The skill does not implement delimiters or instructions to treat user input as data, potentially allowing embedded prompts to influence agent behavior.
- Capability inventory: The skill generates textual reports and delegates market research to the external tool 'everything-claude-code:market-research'.
- Sanitization: No input validation or sanitization routines are defined for user-provided content.
Audit Metadata