AGENT LAB: SKILLS

oauth-implementation

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: 0.90). The prompt includes hardcoded client secrets, private keys, and plaintext signing keys in multiple example implementations (e.g., 'super-secret-key', 'secret123', "secret-key" and embedded RSA blocks), which encourages the LLM to emit secret values verbatim rather than using safe mechanisms like environment variables or key management.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 15, 2026, 08:21 PM