vanilla-lynx
Fail
Audited by Snyk on Nov 18, 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 external-bundle example fetches and executes code from a hardcoded third-party CDN URL on a user tap, which is unvetted remote code execution but is disclosed, user-initiated, and not shown to be covert or deceptive.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata