The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes task data which could potentially contain embedded instructions.- Ingestion points: Task data retrieved via agent-team task list and agent-team task show commands mentioned in SKILL.md.- Boundary markers: Explicitly marked as read-only with instructions to redirect write operations to task-orchestrator.- Capability inventory: Limited to read-only CLI commands for task inspection. No file writing or network capabilities are present.- Sanitization: No specific sanitization or validation of the task content is defined.

task-inspector