glmocr-handwriting
Warn
Audited by Snyk on Sep 16, 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 agent processes image or PDF inputs via URL or local file through the ZhiPu GLM-OCR API, where URLs supplied by the user/attacker are actively fetched and OCR-processed into text ingestion.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata