feynman-technique

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a set of markdown instructions and examples for applying the Feynman Technique. It does not include any scripts (Python, Node.js, or Shell) or tools that perform automated actions. All logic is contained within the prompt instructions for the AI to follow as a cognitive framework.
  • [SAFE]: The external links included in SKILL.md and references/sources.md point to the author's official GitHub repository (github.com/deciqAI), their primary website (deciqai.com), and reputable academic/reference sites like archive.org and caltech.edu. These are used for documentation and attribution rather than remote code execution or data exfiltration.
  • [SAFE]: The YAML frontmatter does not request any restricted tools or permissions. It strictly defines the activation conditions for the AI agent to initiate a teaching/coaching role.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill uses standard markdown formatting and clear instructional language.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 08:14 AM
Security Audit — agent-trust-hub — feynman-technique