search-brain

Fail

Audited by Snyk on Mar 5, 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 injects the raw user-provided $ARGUMENTS into command patterns (Grep/Glob) and into the output heading, so any secret given as the query would be echoed verbatim in commands and responses.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 5, 2026, 11:46 PM