proposal-ideate

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime workflow only instructs the agent to (optionally) run an internal literature-search script against trusted external scholarly APIs (Crossref/DBLP/arXiv) for “the idea’s core terms,” and it does not describe ingesting arbitrary outsider-authored free text without first selecting specific query terms and sources.