NYC

feature-investigation

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: 0.80). This skill explicitly requires extracting and "show[ing] actual code" and configuration values as evidence (including config/dependency fields and full file contents), so if secrets are present in the codebase the agent would likely reproduce them verbatim and risk exfiltration.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:32 AM