deep-work
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructional prompts intended to guide a user through a productivity framework. No scripts, binaries, or automated tool calls are present.
- [SAFE]: External URLs within the skill point to the vendor's website (deciqai.com), their GitHub repository, and Stanford University's faculty pages. These are well-known and reputable sources used for documentation and reference purposes.
- [DATA_EXFILTRATION]: No patterns for accessing sensitive files (such as .ssh or .aws credentials) or exfiltrating data to external servers were detected.
- [PROMPT_INJECTION]: The instructions follow a standard coaching flow using wait markers and do not attempt to bypass AI safety guardrails or override system instructions.
Audit Metadata