Self-Direction
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates by observing user interactions and recording preferences to local markdown files. No network operations or external data transmissions were detected.
- [SAFE]: Access is restricted to the specific configuration directory '~/self-direction/' as defined in the skill metadata, adhering to the principle of least privilege for its stated purpose.
- [SAFE]: No use of dangerous system commands, remote code execution, or obfuscated scripts was found across any of the analyzed files.
- [SAFE]: The skill includes built-in safety mechanisms such as confidence levels and validation prompts to ensure the agent asks for clarification before acting on uncertain inferences.
Audit Metadata