minimax-image-understanding
Fail
Audited by Snyk on Feb 18, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to "transcribe it exactly" and "extract all text from this image" (OCR), which would cause the LLM to output any API keys, tokens, or passwords visible in images verbatim, enabling secret exfiltration.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's Image Processing section explicitly says it downloads images from HTTP/HTTPS URLs (e.g., "https://example.com/image.jpg") and then analyzes them, meaning the agent will fetch and interpret arbitrary public web images (untrusted third-party content) as part of its workflow.
Audit Metadata