stitch-mcp
Warn
Audited by Socket on May 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's design purpose is coherent, but it disproportionately steers agents toward a non-Google proxy CLI as the primary path and routes API/OAuth handling through that third-party tool. Because the recommended CLI is external to Google and may receive credentials while performing broad setup/configuration, this is a high security risk supply-chain and credential-forwarding pattern, though not confirmed malware.
Confidence: 88%Severity: 84%
Audit Metadata