The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions provide a comprehensive guide for the agent to use the qwenpaw cron command-line utility for task management (SKILL.md).
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for scheduling tasks that ingest untrusted or user-defined content, creating a potential vulnerability to indirect prompt injection.
Ingestion points: External data is ingested through the --text parameter and the -f flag for JSON job specifications in the qwenpaw cron create command (SKILL.md).
Boundary markers: The skill lacks instructions for implementing delimiters or security markers to separate user-provided task content from system instructions.
Capability inventory: The skill utilizes shell command execution via the qwenpaw toolset (SKILL.md).
Sanitization: There is no evidence of sanitization, validation, or escaping of the input provided to scheduled tasks.

cron