serp-gap-analysis

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches live Google SERP data using add_or_update_keyword and saves a top-10 SERP snapshot (references/input-and-library.md), then instructs the agent to inspect URLs/titles/snippets (references/winnability-rubric.md) and to call analyze_serp(...) whose output is used directly to drive verdicts and recommendations, so untrusted public web content can materially influence the agent's actions.