The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Node.js coordination scripts (agent_runner.mjs and cli.mjs) located in the shared/ directory. These scripts are used to perform health checks on agents, manage worker execution, and record checkpoints.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted external data which is then used to generate prompts for downstream AI reviewers.
Ingestion points: PHASE_1_DISCOVERY (ingests Story AC, Technical Notes, and project context from files or user input).
Boundary markers: Absent. The skill does not employ specific delimiters or "ignore previous instructions" warnings when interpolating external content into the traceability_prompt.md file used in Phase 3.
Capability inventory: The skill possesses Bash execution capabilities, file system write access, and the ability to delegate tasks to other worker skills.
Sanitization: Absent. There is no evidence of validation or sanitization of the story content before it is processed and passed to other components.

ln-300-task-coordinator