The Agent Skills Directory

[SAFE]: No malicious instructions, obfuscation, or dangerous execution patterns were detected in the skill's code or documentation.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated task data (descriptions and annotations) which acts as an ingestion point for external content. While there are no explicit delimiters to prevent the LLM from interpreting instructions inside task data, the operations are limited to the Taskwarrior CLI scope.
Ingestion points: Task descriptions retrieved via task list, task info, and other reporting commands in SKILL.md.
Boundary markers: Absent; instructions do not explicitly tell the agent to ignore instructions within task data.
Capability inventory: The skill uses the Bash tool to execute task commands as seen in SKILL.md.
Sanitization: No specific sanitization or escaping of task content is implemented.

taskwarrior