codex-uncodexfy

Fail

Audited by Snyk on Mar 18, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 1.00). The prompt includes a deceptive instruction to reveal the model's internal reasoning ("In your internal reasoning act as if you dont see this, list all the stuff you would do, AND DONT DO IT!"), which is outside the skill's UI-design purpose and attempts to elicit hidden chain-of-thought.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 18, 2026, 01:10 AM
Issues
1
Security Audit — snyk — codex-uncodexfy