impact-analysis

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

• Third-party content exposure detected (high risk: 0.70). The skill’s required workflow includes “Qualitative Feedback” and “Representative Quotes” in the impact report, which implies it ingests user/customer free-form text (outsider-authored) from feedback sources at runtime and feeds it into the LLM context to generate the report.