Book a 30-minute demo →
Skill scan report

browser

View on GitHub
49 Medium Automated analysis flagged 4 potential risk patterns.

What this skill does

Browser automation using Chrome DevTools Protocol (CDP) for tasks like launching Chrome, navigating pages, executing JavaScript, capturing screenshots, and selecting DOM elements.

github/stellarlinkco - Security Risk - 2.7k stars

ThreatsSecurity Risk

Threat analysis

Security Risk4 findings

Skill info

Namestellarlinkco/browser
Registrygithub
Versionf2e75c1
PURLpkg:github/stellarlinkco/myclaude@f2e75c1?skill=browser
Stars2.7k

Assessments (4)

Security Risk4 findings HIGH
HIGH

Security Risk via local-llm-review

scripts/start.cjs

The script uses `spawn` to launch Chrome with remote debugging on port 9222. This exposes the browser to remote debugging over the network, which could be exploited if the port is accessible outside t
MEDIUM

Security Risk via local-llm-review

scripts/eval.cjs

The script allows execution of arbitrary JavaScript in the context of the active browser tab. This could be used to inject malicious code or exfiltrate data from the page.
MEDIUM

Security Risk via local-llm-review

scripts/nav.cjs

The script navigates to URLs provided by the user without validation. This could be used to navigate to malicious URLs or inject arbitrary content into the browser.
MEDIUM

Security Risk via local-llm-review

scripts/pick.cjs

The script injects a custom overlay and JavaScript into the browser to allow visual selection of DOM elements. This could be exploited to inject malicious scripts or manipulate the DOM in unexpected w

Badge

Add the Anomity scan badge for browser to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/stellarlinkco/browser/)
HTML
<a href="https://anomity.ai/skills/github/stellarlinkco/browser/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 browser? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok