token-optimizer

Fail

Audited by Snyk on Feb 27, 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 explicitly tells the model to preserve exact values for auth tokens, API keys, credentials, and "Never Compress" secrets (including when converting data to TOON), which forces the LLM to copy and output secret values verbatim if they appear in input.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 27, 2026, 08:14 AM