ln-300-task-coordinator

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 3 "Conditional external traceability validation" (SKILL.md) mandatorily loads references/agent_delegation_pattern.md and launches external advisors via references/agents/agent_runner.mjs — that delegation pattern explicitly allows passing file paths or URLs for the advisor to read, and the advisor's JSON result is parsed to adjust the readiness_score and drive replanning, so untrusted third‑party (arbitrary URL/public web) content can be ingested and materially influence decisions.