ClawHub
Back to skill

Security audit

Cloudflare Browser Run

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed connector wrapper for read-oriented Cloudflare Browser Run tasks, with setup and credential behavior described clearly.

Install this only if you intend to use OOMOL's oo CLI with a connected Cloudflare Browser Run account. Be aware that the first setup can involve a shell-based CLI install, account login, and connecting Cloudflare credentials through OOMOL; review URLs and payloads before rendering private or sensitive pages.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description instructs the agent to use this skill for ANY Cloudflare Browser Run request, which is an overly broad routing rule rather than a narrowly scoped invocation condition. This can cause the skill to activate in situations where a direct API/tool decision or a more specific skill would be safer or more appropriate, increasing the chance of unintended external requests and reducing user-intent precision.

Static analysis

No suspicious patterns detected.