processing-pdf
Warn
Audited by Snyk on Aug 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text from user-supplied PDFs (including scanned PDFs) via
pdftotext/pdfplumbertext extraction and/or converting pages to images then having the LLM extract content (to_images.py+ LLM vision), so attacker-controlled PDF contents are ingested without any selection of a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata