prompt-engineering

Fail

Audited by Snyk on Feb 24, 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's "Core Principle" requires displaying the complete prompt text verbatim, which would force the agent to reproduce any embedded secrets (API keys, tokens, or passwords) and therefore creates an exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 24, 2026, 05:58 AM