stories

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Phase 3 "Ground" and investigation steps instruct the agent to dispatch /worldmodel with "2 web probes" and to perform web searches or run /research or /analyze subagents to ingest public web content, which the agent must read and use to inform framing and decisions (see SKILL.md Phase 3 "Ground" and "Investigating gaps"), exposing it to untrusted third‑party content.