Back to skill

Security audit

邮件免费版

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only helper for searching Gmail and Outlook mail through the porteden CLI, with some privacy and credential-handling cautions users should notice.

Install only if you are comfortable letting the agent use porteden to read search results from your active Gmail or Outlook account. Prefer the keyring login path, avoid saving `PE_API_KEY` in shell profiles or shared scripts, use narrow searches, and fetch full message bodies only when needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The invocation guidance is too broad and lacks explicit activation boundaries, which can cause an agent to invoke this skill whenever a user mentions email-related tasks. In a skill that reads live mailbox contents, overbroad triggering can lead to unnecessary or unintended access to sensitive personal or business email data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill accesses live Gmail/Outlook mailbox data but does not prominently warn about the privacy implications of exposing personal or corporate email content to the agent context. Because email often contains credentials, financial data, legal communications, and internal business information, insufficient disclosure increases the risk of accidental overexposure.

Credential Access

High
Category
Privilege Escalation
Content
### 4. keyring 不可用

- **现象**:`porteden auth login` 报 keyring access denied
- **处理**:检查系统钥匙串服务,或改用 `PE_API_KEY` 环境变量

### 5. 正文过大导致 token 超限
Confidence
74% confidence
Finding
keyring

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.