paddleocr-doc-parsing

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

• Third-party content exposure detected (low risk: 0.10). The skill parses documents from arbitrary user-provided URLs or local file paths via scripts/layout_caller.py and scripts/lib.py, ingesting extracted document text into the agent context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime HTTP requests to an arbitrary user- or environment-supplied API endpoint (PADDLEOCR_DOC_PARSING_API_URL or default paddleocr.com services) without strong first-party verification of the dynamic domain endpoint, constituting a weak/unknown external operational dependency.