right-to-object

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests the data subject’s objection “grounds” via the skill runtime CLI argument --grounds (and related free-text fields like --activity), which is outsider-authored free text from a data subject rather than the operating user; this text is then placed into the LLM context as part of the agent’s processing/response generation.