paper-outline-author

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow for this skill takes as input a user-provided research topic/preference brief and a curated source pack, then has the model generate an outline using those inputs; thus the LLM ingests outsider-authored free text from those user fields (not just trusted first-party docs/API schemas).