setup-gbrain
Fail
Audited by Snyk on Nov 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate gbrain setup flow with no obfuscation, pretext, impersonation, or covert trigger, but it silently records a machine-wide code-intelligence provider and auto-enables artifact pushes to a git remote without asking, which is risky to the user without showing malicious intent.
Issues (1)
E004
CRITICALPrompt injection detected in skill instructions.
Audit Metadata