conversation-search

Fail

Audited by Snyk on Feb 26, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). This skill explicitly retrieves and outputs past conversation content and executed commands verbatim (session JSONL, "Commands Run", etc.), so if secrets were ever pasted into history the agent would be asked to reproduce them, creating a direct exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 26, 2026, 08:59 AM