Cloudflare Email Service

• Outcome: Pass
• Latest audit: Jun 11, 2026 at 7:11 AM UTC
• Version:
  1.0.0

Overview

This is a documentation-only skill for using Cloudflare Email Service, with real email-sending and routing capabilities that should be used deliberately.

Install this only if you want an agent to help configure or use Cloudflare Email Service. Before allowing commands or API calls, confirm the sender, recipients, content, attachments, routing changes, and whether a message will actually be sent. Use least-privilege Cloudflare tokens, keep them in secrets or environment variables, avoid logging them, and do not send sensitive content unless that is explicitly intended.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description is extremely broad and explicitly claims applicability to nearly any email-related request, including simple prompts and coding-agent use. That increases the chance the skill will be auto-invoked in contexts involving sensitive content or outbound communications without sufficiently narrow scoping or confirmation, creating unnecessary privacy and action risks.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill instructs on sending, routing, forwarding, and REST API use with Bearer tokens, but does not warn that these actions can transmit user data to external recipients or third-party infrastructure. In an agent setting, omission of side-effect and privacy warnings can lead to unintended disclosure of sensitive information or execution of externally visible actions without informed user confirmation.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The documentation instructs users to send recipient addresses, message bodies, headers, and attachments to a third-party email API but does not warn about privacy, consent, data handling, or regulatory considerations. In an agent skill context, this omission is meaningful because an automated agent may forward sensitive user content externally without surfacing that action to the operator or end user.

VirusTotal

60/60 vendors flagged this skill as clean.