keyword-cluster-architect

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

• Third-party content exposure detected (high risk: 0.90). This skill's Workflow Step 2 explicitly instructs the agent to use "web_search" to fetch related searches and "People Also Ask" from the public web, meaning it ingests untrusted third‑party content that the agent must read and that directly influences keyword selection and downstream actions.