yc-6-growing-and-monetizing

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for educational purposes, providing summaries and frameworks from Y Combinator's curriculum. It implements an interactive workbook that uses standard user interaction tools to collect business data for a self-assessment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data collected during the interactive assessment phase.
  • Ingestion points: Responses provided by the user via the AskUserQuestion tool during the interactive workbook session defined in SKILL.md.
  • Boundary markers: None explicitly defined to separate user input from the final synthesized assessment.
  • Capability inventory: The skill writes generated assessments and workbook results to the local filesystem within the knowledge/yc-startup-school/ directory.
  • Sanitization: No explicit sanitization or validation of user input is specified before inclusion in the final saved files.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 10:27 PM
Security Audit — agent-trust-hub — yc-6-growing-and-monetizing