feynman-learning
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed exclusively of Markdown documentation and YAML configuration files providing pedagogical instructions. It does not contain executable scripts (Python, Bash, Node.js) or binary files.
- [SAFE]: External references to the
pengsida/learning_researchGitHub repository are used solely for academic attribution and as a source for learning methodologies. No remote code execution or automated script downloads are performed. - [SAFE]: No sensitive data access, hardcoded credentials, or persistence mechanisms were identified in the skill files.
- [SAFE]: The skill follows least-privilege principles by scope-limiting the agent's behavior to specific 'depth branches' (learning modes) based on user intent.
- [SAFE]: There are no signs of obfuscation, prompt injection, or attempts to bypass safety filters.
Audit Metadata