keyword-research

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call third‑party APIs (notably SerpAPI's search.json organic_results/related_questions and SemRush/DataForSEO domain_organic and phrase endpoints) and to parse snippets, organic results, competitor pages and user-facing search content from arbitrary public websites—untrusted, user-generated or public web content that the agent is expected to read and act on, exposing it to indirect prompt injection risk.