Practitioner Research Skill

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly requires collecting and interpreting public third-party content — e.g., "Portfolio evidence — Public GitHub repos" in Evidence Collection, "Session Types: Literature search — Find and cite prior art" and the "Fact-Checking Protocol" that verifies DOIs/links — so the agent would ingest untrusted web content that could influence decisions.