task

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to dispatch commands to a specific tool named tasker_cmd. This is the primary intended functionality of the skill for task management purposes using the vendor-specific CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied strings for task titles, details, and notes, which are passed to the tasker_cmd tool. The instructions mitigate potential injection risks by directing the agent to wrap user inputs in double quotes (e.g., add "<task>") and only split on explicit pipe characters. This represents a standard ingestion surface for task-management functionality and is considered low risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 12:14 PM