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
Risk Level
HIGH
Analyzed
Feb 15, 2026, 09:44 PM