prospecting

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

• Third-party content exposure detected (high risk: 0.75). High likelihood: the required runtime workflow includes browser-assisted research and programmatic extraction (Firecrawl/Browserbase) from outsider-authored public web pages and individual prospect websites, whose readable text can contain prompt-injection content that the agent may ingest into the LLM context.