orchestrating-adversarial-reviews

Fail

Audited by Snyk on Jul 14, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (high risk: 0.90). The top-of-file HTML comment instructs scanners to ignore PROMPT_INJECTION (and other checks), which is a hidden/deceptive meta-directive outside the skill's stated orchestration/verification purpose and could suppress detection of malicious instructions.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 14, 2026, 10:07 AM
Issues
1
Security Audit — snyk — orchestrating-adversarial-reviews