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
CRITICALPrompt injection detected in skill instructions.
Audit Metadata