codex

Fail

Audited by Snyk on Apr 25, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill explicitly preserves and pipes the user's prompt verbatim to a CLI and returns Codex's final message, so any API keys/passwords included in the prompt would be handled and echoed verbatim by the agent, creating exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 25, 2026, 01:27 PM
Issues
1