blackbox
Warn
Audited by Socket on Sep 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s purpose is coherent, and routing prompts/code to Blackbox is expected for an external coding agent. However, the install trust is not coherent: the documented package/repo names conflict with vendor materials, and the claimed open-source repo is not reliably verifiable. That makes the required CLI an effectively unverifiable dependency that then receives credentials and project context, creating a high supply-chain and credential-forwarding risk. No direct evidence of malware or hidden exfiltration beyond the stated vendor flow was provided, so this is better classified as suspicious/high-risk than malicious.
Confidence: 92%Severity: 83%
Audit Metadata