fulltext-skills

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

• Third-party content exposure detected (low risk: 0.10). The skills guide instructions on how to interact with external academic preprint servers and repositories like arXiv, PubMed Central, and CORE, but the workflow does not automatically ingest outsider-authored free text without the user first selecting specific items.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The zotero-ai-butler-guide skill instructs the user to download an external add-on release asset from an arbitrary third-party GitHub repository (https://github.com/steven-jianhao-li/zotero-AI-Butler), which is an unverified external runtime dependency carrying a high risk tier.