The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches and processes ticket data (such as titles and descriptions) which are considered untrusted external inputs.
Ingestion points: Data enters the skill context through the cawplan tickets poll command execution described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between ticket data and instructions, nor are there commands to ignore embedded instructions.
Capability inventory: The skill utilizes the Bash tool to execute cawplan CLI commands and process results.
Sanitization: No sanitization or filtering logic is specified for the ticket fields before they are aggregated and reported to the user.

cawplan-plan-track