lmstudio-subagents
Fail
Audited by Snyk on Mar 6, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt includes explicit Authorization: Bearer lmstudio headers in multiple curl/exec examples, which requires the agent to emit a bearer token string verbatim (credential exposure pattern).
Audit Metadata