ai-startup-school

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and its 15 reference files were scanned for malicious patterns including prompt injection, data exfiltration, and persistence mechanisms. No such behaviors were detected.
  • [DATA_EXPOSURE]: The skill collects user responses for a strategy assessment and saves them to a local path (knowledge/yc-startup-school/ai-startup-school-workbook.md). This behavior is transparent, documented in the instructions, and stays within the agent's expected workspace.
  • [PROMPT_INJECTION]: The skill instructions and transcripts do not contain markers designed to bypass safety filters or override system instructions. The 'Interactive Workbook' uses standard tool calls to facilitate user dialogue.
  • [EXTERNAL_DOWNLOADS]: The reference files include URLs for informational attribution to YouTube and the Y Combinator library. These are well-known services and no runtime downloads or remote code executions are initiated by the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 10:28 PM
Security Audit — agent-trust-hub — ai-startup-school