browser-automation
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The browser automation purpose matches the capabilities, and data flows go directly to target websites rather than an obvious exfiltration service. However, the core ${CLAUDE_PLUGIN_ROOT}/bin/* executables are not provenance-verified in the provided material, and the skill enables automated actions within persistent logged-in sessions, including shopping/form submission. Main concern is install trust and real-world action scope, not confirmed malware.
Confidence: 84%Severity: 72%
Audit Metadata