synthetic-search

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs using Synthetic's web search API (POST https://api.synthetic.new/v2/search) to fetch results including results[].url and results[].text from arbitrary public websites, which the agent is expected to read and could therefore allow indirect prompt injection.