aiconfig-projects
Fail
Audited by Snyk on Feb 15, 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 instructs the agent to detect or prompt for LaunchDarkly API tokens (from env/config or the user) and to embed them verbatim in API calls and example code (e.g., curl Authorization header, SDK init), requiring the LLM to handle and output secrets directly.
Audit Metadata