core
What this skill does
Browser automation tool for AI agents, used to interact with websites, fill forms, extract data, and automate tasks in a browser.
github/vercel-labs - Security Misconfiguration - 40.4k stars
Threat analysis
Skill info
pkg:github/vercel-labs/agent-browser@548b159?skill=coreAssessments (2)
Security Misconfiguration
Security Misconfiguration via local-llm-review
references/authentication.md
The skill provides instructions on how to start Chrome with remote debugging enabled (`--remote-debugging-port=9222`), which exposes full browser control on localhost. This is a potential security risSecurity Misconfiguration via local-llm-review
templates/authenticated-session.sh
The script provides a template for authenticating with a site using environment variables (`APP_USERNAME` and `APP_PASSWORD`). If not handled securely, this could expose credentials in logs or to unauBadge
Add the Anomity scan badge for core to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of core? Report an issue or request a rescan.
