liantis

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can be ingested at runtime via Apideck’s HRIS connector calls (e.g., employee/time-off records returned as readable JSON/text from the Liantis tenant API) and/or via the Proxy API path that forwards responses from the user-specified Liantis downstream endpoint into the agent’s LLM context.