money-content

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

• Third-party content exposure detected (high risk: 0.90). The skill's Stage 1 Research explicitly requires ingesting public web content—e.g., "read codebase, landing page, docs" and "Analyze competitor content (what ranks, what converts)"—so the agent is expected to fetch and interpret untrusted third‑party pages whose instructions or claims could materially influence its content-generation and publishing actions.