superplan

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

• Third-party content exposure detected (high risk: 0.90). This skill instructs the agent to perform open web research and parallel web searches (see Phase 4: RESEARCH / Execution Guide Step 4 — "launch parallel web searches" and the Plan Template's "Research & Best Practices" / Appendix "Research Sources" with external URLs), so it clearly ingests untrusted public third‑party content as part of its workflow.