planguage-author

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

• Third-party content exposure detected (high risk: 0.70). The required workflow explicitly starts from “source material” such as “interview notes, story text, standards, or defect reports” and then normalizes/splits that content into the LLM output context, so if that source is outsider-authored free text, it will be ingested at runtime via the user-provided input.