personal-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE] (SAFE): All personal data and task information are stored in a local directory (~/.claude/personal_assistant/) controlled by the user.
- [COMMAND_EXECUTION] (SAFE): The scripts/task_helper.py script manages tasks via standard CLI arguments and does not utilize unsafe execution functions like eval() or os.system() on user-provided input.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes user-supplied task titles and descriptions which are stored locally. While this provides a surface for indirect instructions, the skill's capabilities are limited to local data management. (1) Ingestion: scripts/task_helper.py arguments; (2) Boundaries: Absent; (3) Capabilities: Local task/context storage; (4) Sanitization: Not found in current scripts.
Audit Metadata