grill-me

Fail

Audited by Snyk on Apr 24, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). The skill mandates reading arbitrary files and using their contents as the plan (and also exploring the codebase), which can cause the model to ingest and reproduce secret values verbatim in questions or recommendations, creating an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 24, 2026, 05:05 AM
Issues
1