clado

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

• Third-party content exposure detected (high risk: 0.75). The required workflow includes calling Clado endpoints like /api/search/deep_research/* and /api/enrich/scrape with user-supplied query/linkedin_url, where the service may fetch and return scraped public web/LinkedIn text into the agent’s LLM context as results (outsider-authored free text via runtime API responses).