paul-graham-perspective

Pass

Audited by Gen Agent Trust Hub on May 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a personality emulation for Paul Graham, utilizing a robust set of research data in the references/research/ directory. The instructions focus on character consistency, logical reasoning, and helpful advice.
  • [PROMPT_INJECTION]: The skill employs an 'Agentic Protocol' that ingests data from external web searches to analyze startups and founders. While this creates a surface for indirect prompt injection from third-party websites, the risk is inherent to any research-oriented tool and is considered low given the skill's primary focus on generative text advice without high-privilege capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
May 30, 2026, 11:15 AM
Security Audit — agent-trust-hub — paul-graham-perspective