ClawHub
Back to skill

Security audit

Cloudflare MCP

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for operating Cloudflare through OOMOL, but its setup instructions include unverified remote installer execution and it can perform high-impact Cloudflare writes.

Review this skill before installing if your Cloudflare account has production or administrative access. Only install the oo CLI from a trusted source, prefer official documented installers with verification where available, and confirm every write payload and intended Cloudflare effect before allowing the execute action to run.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
95% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This bypasses integrity verification and gives whoever controls the remote endpoint, CDN path, or transport chain immediate code execution on the host running the skill, which is especially risky because the content is presented as an automatic remediation step inside an operational workflow.

Content

Scanner excerpt · SKILL.md (reported line 57)May include surrounding context.

Static analysis

No suspicious patterns detected.