text-in-image
Fail
Audited by Snyk on Jul 9, 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 requires the model to include user-provided strings "verbatim" in prompts and structured JSON (quoted text fields), so any secret the user supplies would be reproduced exactly and exposed to downstream systems—an exfiltration risk.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata