glmv-caption
Warn
Audited by Snyk on Apr 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts arbitrary image/video/file URLs (see "Supported Input Types" in SKILL.md and the scripts/glmv_caption.py functions process_image/build_content which include http(s) URLs and send them to the GLM API), so untrusted user-provided web content is ingested and interpreted by the model as part of its workflow, which could allow indirect prompt injection via those remote resources.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata