document-image-extractor

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documents (.docx and .pdf), creating a surface for indirect prompt injection.\n
  • Ingestion points: extract_from_docx and extract_from_pdf in scripts/extract_images.py ingest file paths and process document content.\n
  • Boundary markers: Absent. The skill does not use delimiters or instructions to ignore commands embedded within the documents.\n
  • Capability inventory: The script can create directories and write files to the local file system via Path.mkdir and open(..., "wb").\n
  • Sanitization: Absent. The script relies on third-party libraries (python-docx, pymupdf) for parsing without additional validation of the file contents or metadata.\n- [DYNAMIC_EXECUTION]: The script disables security guardrails designed to prevent resource exhaustion attacks.\n
  • Evidence: Image.MAX_IMAGE_PIXELS = None in scripts/extract_images.py disables Pillow's protection against "decompression bomb" attacks. This allows the processing of images with extreme dimensions, which could lead to memory exhaustion and a Denial of Service (DoS) when a malicious document is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:14 PM