daily-task-manager

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust task management system with 'fail-closed' logic for ambiguous task matches and mandatory confirmation for destructive actions like removal.
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill accesses a specific, non-sensitive file path (ops/tasks.md) for task storage. There are no network operations or external data transmissions.
  • [COMMAND_EXECUTION]: The skill explicitly forbids shell execution or the use of CLI verbs, mandating the use of the platform's provided get_page and put_page tools instead.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied task descriptions and stores them in markdown. It uses a structured format with clear section headers and HTML comment IDs, which acts as a boundary for the agent context. The severity is low as it is a standard data ingestion surface for a productivity tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 06:18 PM
Security Audit — agent-trust-hub — daily-task-manager