synthetic-search

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md requires calling Synthetic's public web search API (POST https://api.synthetic.new/v2/search) which returns results[].url and results[].text drawn from arbitrary public web pages, so the agent would ingest untrusted third‑party content that could include indirect prompt injections.