Back to skill

Security audit

Email Assistant Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple email-help skill that works on pasted or described email content and does not request mailbox access, execution, persistence, or sending authority.

Before using it, redact secrets, credentials, personal data, and confidential business details from pasted emails when possible, and manually review any generated reply or task list before acting on it.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly asks users to paste email text, which may contain sensitive personal, financial, legal, or business information, but it provides no privacy warning or data-handling caution. In this context, that omission materially raises risk because users may share confidential email contents, client data, or internal tasks without understanding the sensitivity implications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation examples use very generic phrases such as asking to 'help process this email' or 'look at today's emails,' which can overlap with normal conversation and increase the chance of accidental or unintended activation. In a productivity/email context, this is more dangerous because activation could lead users to paste or summarize sensitive business communications without a deliberate decision boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.