ocrmypdf-api
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions and code examples for processing external PDF documents, creating an attack surface for malicious document content.\n
- Ingestion points: The Python API (
ocrmypdf.ocr) and the Flask web service example (request.files['file']) inSKILL.mdingest untrusted PDF files from external sources.\n - Boundary markers: The instructions do not define boundary markers or safety guidelines to mitigate risks from malicious instructions embedded in the processed PDFs.\n
- Capability inventory: The skill enables file system access and invokes the OCRmyPDF engine, which typically executes subprocesses for Tesseract, Ghostscript, and unpaper.\n
- Sanitization: The documentation does not specify sanitization or content validation procedures for the ingested PDF data.\n- [EXTERNAL_DOWNLOADS]: The skill references the installation of several Python packages for extending OCR capabilities.\n
- The documentation suggests installing packages such as
ocrmypdf-easyocr,ocrmypdf-paddleocr, andocrmypdf-appleocrto integrate alternative OCR engines.
Audit Metadata