license-compliance

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md specifies that runtime LLM output must incorporate “output the user pastes or attaches” as scan input and to treat that pasted text as scan output for reporting, so outsider-authored free text is ingested directly into the workflow without selecting a specific item first.