Skill scan report

autoglm-browser-agent

View on GitHub

45 Medium Automated analysis flagged 3 potential risk patterns.

What this skill does

Browser automation agent for tasks like opening websites, searching, social media interaction, form filling, etc.

github/leoyeai - Excessive Agency - 2.1k stars

ThreatsExcessive Agency Untrusted Code Execution

Threat analysis

Excessive Agency1 finding

Untrusted Code Execution2 findings

Skill info

Nameleoyeai/autoglm-browser-agent

Registrygithub

Versione5199b5

PURLpkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=autoglm-browser-agent

Stars2.1k

SourceView on GitHub

Assessments (3)

Excessive Agency1 finding HIGH

HIGH

Excessive Agency via local-llm-review

SKILL.md

description: >-\n  智能浏览器自动化代理,可执行任何需要浏览器的任务。\n  包括但不限于:打开网页、搜索信息(百度/谷歌/必应)、浏览社交媒体(微博/小红书/知乎/抖音/B站)、\n  点赞/评论/转发/收藏、发帖/发消息、登录网站、填写表单、截图、采集网页内容、\n  在线购物比价、查看新闻资讯、操作在线文档(飞书文档/腾讯文档等)。\n  当用户提到任何网站名称、网址URL

Untrusted Code Execution2 findings MEDIUM

MEDIUM

Untrusted Code Execution via local-llm-review

INSTALL.md

执行以下命令解除：\n\n```bash\nxattr -d com.apple.quarantine {baseDir}/dist/relay {baseDir}/dist/mcp_server\n```

MEDIUM

Untrusted Code Execution via local-llm-review

SKILL.md

```bash\n# macOS 解除安全限制（首次需要，已执行过则自动跳过）\nxattr -d com.apple.quarantine {baseDir}/dist/relay {baseDir}/dist/mcp_server 2>/dev/null; true\nmcporter list autoglm-browser-agent --schema\n```

Badge

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

Markdown

[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/leoyeai/autoglm-browser-agent/)

HTML

<a href="https://anomity.ai/skills/github/leoyeai/autoglm-browser-agent/"><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 autoglm-browser-agent? Report an issue or request a rescan.