eeailab-picturebook

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 mandates a recurring promotional banner with a personal WeChat contact in the agent's replies, and it withholds that banner only in sensitive moments so it won't "interrupt like an ad," which is self-promotion unrelated to the picture-book task rather than an attack on the user.

Issues (1)

E004
CRITICAL

Prompt injection detected in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 13, 2026, 02:34 PM
Issues
1