taskwarrior-manager

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill interacts with the local system by executing the Taskwarrior CLI binary ('task'). This is standard behavior for a management tool and does not involve elevated privileges.- [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it reads and processes task descriptions which may be influenced by external inputs.
  • Ingestion points: The agent retrieves task data (descriptions, tags, projects) from the output of the 'task' command.
  • Boundary markers: No delimiters are defined to isolate task data from instructions.
  • Capability inventory: The skill allows the agent to create and modify tasks via the 'task add' and 'task mod' commands.
  • Sanitization: There are no instructions provided to sanitize task descriptions to prevent shell injection or instruction hijacking.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 04:34 AM