cardiology-topol-writer

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly "Accept[s] whatever the user provides" (Process step 1: "Receive the Thought Dump") and expects to read and interpret user-supplied research papers, notes, or links to primary sources as part of its workflow, which exposes the agent to untrusted third‑party content that could carry indirect prompt injection.