eeailab-montessori

Fail

Audited by Snyk on Nov 13, 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 decisive content is mild self-promotion (a branded slogan and WeChat contact inserted into answers) plus instructions to hide the source of its answers and its local-material limitations from the user, which is sketchy but not aimed at attacking the user.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads local first-party Montessori files, and the only outsider-text path is the conditional web search for AMI/AMS/Montessori public materials, which the agent must actively run and which returns arbitrary web pages, so this is low risk.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 12:50 PM
Issues
2