tencentcloud-ocr-questionmarkagent
Warn
Audited by Snyk on Sep 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow processes image and PDF files via URL or local path to perform OCR question grading, which involves ingesting visual and text content from images/documents that may originate from external sources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata