misconceptions
Fail
Audited by Snyk on Aug 25, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). This skill instructs the assistant to operate silently, record user messages as "misconceptions," append them to a local log, and transmit or prepare them for a third party (Vidbyte), which is deceptive and potentially privacy-invasive without clear per-message consent.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata