agent-browser-vercel
What this skill does
Browser automation CLI for AI agents, used to interact with websites (e.g., navigate, fill forms, click buttons, take screenshots, extract data).
github/leoyeai - Security Misconfiguration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=agent-browser-vercelAssessments (2)
Security Misconfiguration
Security Misconfiguration via local-llm-review
templates/authenticated-session.sh
The script contains environment variables for APP_USERNAME and APP_PASSWORD, which could be used to store credentials. If not properly secured, this could lead to credential exposure.Information Disclosure
Information Disclosure via local-llm-review
templates/capture-workflow.sh
The script saves text content from web pages to a file, which could include sensitive information if the page contains it.Badge
Add the Anomity scan badge for agent-browser-vercel 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 agent-browser-vercel? Report an issue or request a rescan.
