kimi-webbridge

Warn

Audited by Socket on Aug 23, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

Official same-org browser automation skill with coherent purpose and no clear credential-harvesting endpoint, but it is intrinsically high-risk because it grants an AI broad control over the user's authenticated browser, file upload/write capability, and low-level CDP/network access. Not confirmed malware; security risk is high due to power and scope.

Confidence: 90%Severity: 76%
Audit Metadata
Analyzed At
Aug 23, 2026, 01:36 PM
Package URL
pkg:socket/skills-sh/moonshotai%2Fkimi-code%2Fkimi-webbridge%2F@e0915b627ba42eccfba278effbde544ba95c7e5a0899f3fbcb34c4ecc98256d3
Security Audit — socket — kimi-webbridge