40Medium
The skill performs unauthorized host enumeration and network exfiltration while bypassing security constraints by failing to declare its tool usage and network capabilities.
Skill Info
Namecloudflare/sandbox-sdk/sandbox-bridge
Registrygithub
Version71f67bcc9a0f
PURLpkg:github/cloudflare/sandbox-sdk@71f67bcc9a0f?skill=sandbox-bridge
Stars1,047
Installs11
Source
Install
This skill has findings worth reviewing before installing.
GitHub
11 installs
Skills.shDocs
npx skills add https://github.com/cloudflare/sandbox-sdkAssessments (3)
AI Agent Traps ↗System and OS enumeration — fingerprints the host operating system and hardwaremediumreconnaissanceAML.T0053AML.T0037LLM06:2025LLM02:2025
System and OS enumeration — fingerprints the host operating system and hardware
100% confidenceline 59
uname -a
Pipe to curl/wget for data exfiltration detectedmediumdata exfiltrationAML.T0025AML.T0024LLM02:2025
Pipe to curl/wget for data exfiltration detected
100% confidenceline 89
| curl
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/cloudflare/sandbox-sdk/sandbox-bridge)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/cloudflare/sandbox-sdk/sandbox-bridge"><img src="https://mondoo.com/ai-agent-security/api/badge/github/cloudflare/sandbox-sdk/sandbox-bridge.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/cloudflare/sandbox-sdk/sandbox-bridge.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow