The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted input from user requests to populate task descriptions in local documents. Ingestion points: User input and existing task files in the Docs/Task/ directory. Boundary markers: Absent. Capability inventory: File read and write access to Markdown documents. Sanitization: Absent. This creates an indirect prompt injection surface within the document content, although the risk is limited by the lack of executable capabilities.
[SAFE]: No hardcoded credentials, unauthorized network connections, or remote code execution patterns were detected. The skill focuses solely on organizational document manipulation within a restricted local path.

task-add