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
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:44 AM
Security Audit — agent-trust-hub — startup-idea-evaluator