NYC

workflow-interactive-dev

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The dispatch implementation explicitly parses user-submitted text and returns it verbatim in node outputs and toolResponses, meaning any API keys or passwords supplied by a user would be echoed through the agent and could be exfiltrated.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:12 AM