literature-pdf-ocr-library

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

• Third-party content exposure detected (low risk: 0.10). The skill searches and downloads academic papers from external APIs (arXiv, Semantic Scholar, OpenAlex, Hugging Face), whose metadata and PDF contents are ingested by the agent at runtime.

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

• Potentially malicious external URL detected (medium risk: 0.30). An operational dependency on PaddleOCR's layout-parsing API endpoint is present and used at runtime for OCR conversion.