respondent-panel
Fail
Audited by Snyk on Aug 10, 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 take user-supplied artifacts "verbatim" and pass/quote them to respondents, which will force the model to reproduce any secret values contained in those artifacts in its output.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata