The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructs the agent to process untrusted user input (task descriptions) and use that data to dynamically create sub-tasks and spawn new worker agents. This multi-agent orchestration pattern creates a surface where instructions embedded in the input could influence the agent's logic.
Ingestion points: The <task description> argument defined in the SKILL.md frontmatter is the primary entry point for untrusted data.
Boundary markers: The instructions lack explicit boundary markers or directions for the lead agent to treat the task description as non-executable data, increasing the risk of instruction following from the input.
Capability inventory: The skill utilizes powerful autonomous capabilities including team_spawn_worker (to initiate new agent contexts), task_create, and receive_messages as shown in SKILL.md examples.
Sanitization: There is no mention of sanitization, validation, or filtering of the task description before it is interpolated into the orchestration workflow.

team