pydantic-ai-agent
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: 0.80). The prompt contains examples that embed API keys directly (e.g., LLM_API_KEY=sk-ant-... and api_key="sk-ant-..."/"sk-...") and shows passing api_key literals to provider.create, which encourages including secret values verbatim in generated code or commands and thus creates exfiltration risk.
Audit Metadata