research-assistant

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

• Third-party content exposure detected (high risk: 0.90). This skill's Research Protocol and Topic Monitoring steps (e.g., "Phase 2: Search & Collect" and the "Topic Monitoring"/"Periodic Check Protocol" sections in SKILL.md) explicitly instruct the agent to run web searches, ingest and synthesize open/public sources including community discussion, and then act on those findings (create briefs, trigger alerts), which exposes the agent to untrusted third‑party content that could carry indirect prompt injections.