deep-productivity
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of educational markdown files and interactive Python scripts for personal productivity management.
- [COMMAND_EXECUTION]: The Python scripts (
assess_focus.py,generate_hierarchy.py,track_levers.py) use standard library modules to perform local calculations and interactive command-line interface tasks. They do not execute arbitrary shell commands or access sensitive system paths. - [DATA_EXPOSURE]: Data handling is restricted to the local environment.
generate_hierarchy.pyandtrack_levers.pycreate and update local files (goal_hierarchy.md,lever_tracking.json) in the current directory to store user-provided goal data. No network operations or credentials were found. - [PROMPT_INJECTION]: The instructions are focused on productivity coaching and do not contain patterns typical of jailbreaks or safety filter bypasses.
- [INDIRECT_PROMPT_INJECTION]: While the scripts ingest user input via
input()calls, this data is used for local reporting and file storage. There is no untrusted data ingestion from external APIs or web sources that could influence agent behavior.
Audit Metadata