cc-gateway-ai-proxy
Warn
Audited by Socket on Apr 1, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally coherent, but its core function is to evade Anthropic telemetry and device identity controls by extracting stored OAuth credentials, man-in-the-middling all Claude Code traffic, and injecting centralized auth. Install provenance looks ordinary, but the credential handling, proxying, and explicit identity-masking behavior make this a high-risk skill.
Confidence: 91%Severity: 90%
Audit Metadata