semantic-gap-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md Step 1 "Fetch the URL" and Step 2 "Google the target keyword. Fetch the top 3 results in full") explicitly instructs the agent to fetch and fully ingest arbitrary public web pages (third-party SERP results) and then use that content to drive gap analysis and next actions, so untrusted third‑party content can influence decisions.