adversarial-review

Fail

Audited by Snyk on Nov 12, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill's documentation presents a working adversarial review with blocking behavior and high trust metadata, but the bundled script is an unimplemented scaffold that always exits with an error, and SKILL.md never discloses this, which is a limitation hidden from the user without malicious intent.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 12, 2026, 08:07 PM
Issues
1