Security audit

Temporary Email

Security checks across malware telemetry and agentic risk

Overview

This temporary email skill is mostly purpose-aligned, but it needs review because it can collect an API key in chat and forward full email contents to any configured webhook URL without clear privacy warnings.

Review before installing. Use this only if you trust chat-tempmail.com, configure TEMP_EMAIL_API_KEY through an environment variable or secret manager instead of pasting it into chat, confirm exact IDs before deleting emails or messages, and configure webhooks only to trusted endpoints you control because they can receive message content and metadata.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (5)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill documents irreversible DELETE operations for emails and messages but does not require confirmation, preview the target, or warn the user about data loss. In an agent setting, this increases the chance of accidental or prompt-induced destructive actions against the user's temp mail account.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: Webhook configuration forwards message events to an arbitrary external URL, which can expose email metadata or contents to third parties, yet the skill gives no privacy or data-sharing warning. In practice, an agent could be prompted to configure exfiltration of sensitive inbound mail to an attacker-controlled endpoint.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill tells the agent to ask the user for an API key if the environment variable is missing, but provides no safe handling guidance. Requesting credentials in normal chat can cause secrets to be exposed in conversation logs, retained in transcripts, or mishandled by downstream systems.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The webhook API is documented to send full message contents, including plain text and HTML, to an arbitrary external URL, but the reference provides no privacy, trust-boundary, or data-handling warning. In the context of a temporary email skill, forwarded inbox contents may contain passwords, verification codes, links, or personal data, so configuring a webhook to an untrusted endpoint can cause silent data exfiltration.

Ssd 3

Medium

Confidence: 98% confidence
Finding: Explicitly instructing the agent to collect an API key in chat is a direct secret-handling flaw. This creates a realistic path for credential disclosure through chat history, analytics, screenshots, or prompt injection chains that cause the model to repeat or misuse the key.

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.