anfra-aml

Fail

Audited by Snyk on Nov 19, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate AML modeling guide, but the demo dataset labels itself "[Demo] Ecommerce Official (2025)" with a "Trust/Endorsed" tag, which overstates the authority of sample content and could mislead a user about its trustworthiness; this is a weak, non-malicious sign.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 19, 2026, 03:34 AM
Issues
1