design-polish

Fail

Audited by Snyk on Apr 28, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to obtain user credentials (or read them from .env/lib/config) and to use them for navigation/login and to fill a LOGIN field in the evaluator sub-agent prompt, which requires the LLM to receive and include secret values verbatim in its actions/output — an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 28, 2026, 05:52 AM
Issues
1