ClawHub
Back to skill

Security audit

Cloudflare Mcp

Security checks for vulnerabilities and agentic risk

Overview

This Cloudflare skill is coherent and uses an official-looking MCP endpoint, but it grants broad write-capable Cloudflare API access with weak scoping and limited user-safety instructions.

Review this before installing if you manage production Cloudflare resources. Use the narrowest OAuth permissions available, confirm every DNS, Worker, KV, R2, D1, or account-changing action before execution, and avoid relying on short generic trigger words for unrelated infrastructure work.

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
  • 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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are very broad and include common infrastructure terms like "DNS", "CF", "Workers", and "KV", which can appear in many unrelated user requests. This increases the chance that the skill is invoked unexpectedly and may gain access to Cloudflare-connected capabilities in contexts where the user did not intend to use this skill, especially given its ability to perform write operations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill advertises and enables write-capable operations such as creating DNS records, KV namespaces, and R2 buckets, but it does not clearly warn users that these actions can modify production infrastructure and have security or availability consequences. In combination with automatic endpoint search and execute behavior plus OAuth-granted account access, this raises the risk of unintended or insufficiently reviewed destructive or sensitive changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language instructions, headings, and examples are presented entirely in Chinese, and the file does not indicate that this language choice is optional or region-specific. This can violate language/locale policy when users are not given an opt-in or alternative language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description is written entirely in Chinese and gives no indication that other languages are supported or that the language choice is optional. This can be a natural-language policy issue when a skill presents a fixed language or locale without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.