on-page-seo

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to query and use public third‑party content (e.g., "Step 1: Check if Google knows you" with the Knowledge Graph Search API URL, Tablet 5's LSI methods like Google related searches/autocomplete/People Also Ask, and the Trusted Seeds Strategy referencing Wikipedia/Wikidata/social profiles), and those external, user‑generated/public sources are read and used to drive structured-data, keyword, and entity decisions—exposing the agent to untrusted third‑party content that could influence actions.