onelogin

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

• Third-party content exposure detected (high risk: 0.75). At runtime the skill calls Apideck’s HRIS unified API (and optionally the Proxy API) to fetch OneLogin data, which is outsider-authored content from the user’s OneLogin tenant that the operating user did not author; this data is then ingested into the agent’s LLM context via the API response.