browser-use
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent with social media automation and uses an official same-org tool, so it is not malware-like. However, it enables high-autonomy public posting, messaging, engagement, scraping, and cookie handling on authenticated accounts, creating substantial real-world and account-security risk even with its domain allowlist and prompt-injection guardrails.
Confidence: 90%Severity: 78%
Audit Metadata