content-research-writer

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

• Third-party content exposure detected (high risk: 0.80). The skill's required Step 3 "Conduct Research" (in SKILL.md and references/workflow-templates.md) instructs the agent to search for, fetch, and extract information from public sources (examples include Stack Overflow, McKinsey, Gartner) and add citations, so it will read and act on untrusted third‑party web content that can materially influence its outputs.