Playwright MCP Browser Automation
Warn
Audited by Socket on Mar 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose is coherent with browser automation, but the distribution path is not. The skill presents itself as official Playwright-powered functionality while instructing installation from third-party skill registries (`agentskillexchange`/ClawHub) instead of Microsoft's upstream Playwright MCP package, creating transitive trust and supply-chain risk. No clear credential theft or exfiltration is shown, so this is not confirmed malware, but the install trust model is materially inconsistent with the branding.
Confidence: 87%Severity: 74%
Audit Metadata