deep-read

Fail

Audited by Snyk on Mar 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). This skill mandates reading files in full and producing line-cited reports of code/configuration, so if secrets (hard-coded API keys, tokens, or passwords) exist in the repository the agent would be required to reproduce them verbatim in its output, creating an exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 1, 2026, 01:36 AM