ghostwriter
Fail
Audited by Snyk on Aug 8, 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 mandates assembling the output from the user's exact words and to ask for missing lines instead of inventing them, which forces the model to reproduce any secret the user provides verbatim (high exfiltration risk).
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata