staging-browser-localhost
Fail
Audited by Snyk on Feb 16, 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 retrieve JWT idToken and refreshToken and embed them verbatim as query parameters in a generated command/URL, which requires the LLM to handle and output secret values directly (high exfiltration risk).
Audit Metadata