Back to skill

Security audit

Cloudflare Dns Updater

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it uses a Cloudflare API token to create or update DNS A records, with no hidden persistence or unrelated data collection found.

Install only if you want an agent to make live Cloudflare DNS changes. Use a Cloudflare API token limited to the specific zone and DNS-edit permission, confirm the zone, record, IP address, and proxied setting before each run, and avoid using the public-IP lookup unless that is exactly the address you intend to publish.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill declares no permissions even though its documented behavior requires reading an environment variable and performing network operations against Cloudflare and, in the example, an external IP discovery service. This undermines informed consent and policy enforcement because an agent or platform may treat the skill as less privileged than it actually is.

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill is described as taking a provided IP address as input, but the example instructs the agent to independently discover the server's public IP via an external curl request. That expands the skill's behavior beyond its stated purpose, introduces an undisclosed outbound connection, and can leak environment/network metadata while encouraging autonomous side effects the user may not have requested.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The README explains how to create or update live Cloudflare DNS A records but does not clearly warn that running the skill changes production DNS state and can reroute traffic or break service reachability. In an agent-driven workflow, the lack of an explicit safety warning increases the chance of unintended infrastructure changes from ambiguous prompts or operator misunderstanding.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The description states that the skill creates or updates Cloudflare DNS records but does not clearly warn that using it will modify production DNS state. Without an explicit warning about this side effect, users may invoke the skill without appreciating that it can redirect traffic or disrupt services.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The example workflow makes an outbound request to a third-party service to determine the public IP, but it provides no privacy or disclosure warning. This can expose network information and normalizes contacting external services unrelated to the core DNS update action without informed user consent.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
Confidence
98% confidence
Finding
requests

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
96% confidence
Finding
requests

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.