lead-finding

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

• Third-party content exposure detected (high risk: 0.75). The required workflow explicitly ingests and exports data from multiple outsider-authored sources (e.g., Apollo/Crunchbase/GitHub/job boards/conference websites) into the agent’s runtime context as readable lead lists/CSV-derived text, which can include free-form content and thus creates an indirect prompt-injection risk.