video-to-superprompt
Fail
Audited by Snyk on Jul 19, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). The skill explicitly instructs the agent to ask for and include exact file/URL values and to "include exact URLs when supplied" in the output, which can force the model to echo user-supplied secrets (e.g., presigned URLs, tokens) verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata