seo-traffic-analyzer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Process and AI Agent Integration explicitly direct the agent to run WebSearch probes and WebFetch calls (e.g., Phase 2: "Run a WebSearch for the keyword and scan results"; Phase 3: WebFetch https://www.similarweb.com/website/[domain]/; Wayback Machine fetches) and to read/interpret those public web pages, social/referral mentions, and search results as part of its analysis, which are untrusted third‑party sources that could contain instructions influencing the agent's decisions.