Book a 30-minute demo →
Skill scan report

browser-automation

View on GitHub
49 Medium This skill sends sensitive values to an external host. Automated analysis flagged 1 additional risk pattern.

What this skill does

Browser automation via HTTP server. Supports multiple concurrent sessions for multi-user testing, saved flows, and profile-based auth persistence.

github/civitai - Data Exfiltration - 7.2k stars

ThreatsData Exfiltration Insecure API

Threat analysis

Data Exfiltration1 finding
Insecure API1 finding

Skill info

Namecivitai/browser-automation
Registrygithub
Version159f535
PURLpkg:github/civitai/civitai@159f535?skill=browser-automation
Stars7.2k

Assessments (2)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

server.mjs

The server allows execution of arbitrary code via the /chunk endpoint, which could be used to exfiltrate data from the target system.
Insecure API1 finding HIGH
HIGH

Insecure API via local-llm-review

server.mjs

The server exposes endpoints like /chunk and /navigate that allow remote code execution and navigation, which could be exploited for malicious purposes.

Badge

Add the Anomity scan badge for browser-automation to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/civitai/browser-automation/)
HTML
<a href="https://anomity.ai/skills/github/civitai/browser-automation/"><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-automation? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok