writing-well
Fail
Audited by Snyk on Mar 2, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill requires quoting exact offending text from user-provided input, which could force the model to echo secrets verbatim if they appear in the text, creating an exfiltration risk.
Audit Metadata