agent-browser

Warn

Audited by Socket on Mar 27, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill’s capabilities mostly match its stated browser-automation purpose and the install provenance appears legitimate, but it gives an AI agent broad live web powers, handles sensitive auth/session material, and processes untrusted page content with action-taking ability. This is better classified as a high-risk automation skill than malware.

Confidence: 84%Severity: 74%
Audit Metadata
Analyzed At
Mar 27, 2026, 03:39 AM
Package URL
pkg:socket/skills-sh/wenerme%2Fai%2Fagent-browser%2F@2406f5d1c14a6727a0b628bf84e7485e0f76f8de