Back to skill

Security audit

Gmail Search Emails

Security checks for vulnerabilities and agentic risk

Overview

This Gmail search skill is simple and purpose-aligned, but it can access sensitive mailbox snippets under a broad trigger without an explicit consent or scoping step.

Review before installing. Only use this skill when you intend the agent to search a Gmail account, and prefer confirming the account, query, and whether snippets should be returned before running 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 does not warn that it accesses Gmail message data, yet its output includes email headers and snippets that may contain sensitive personal or business information. Without a clear privacy warning or consent cue, users may not understand that invoking the skill can retrieve and expose mailbox contents.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation condition is broad enough to trigger on ordinary requests to find emails or communications, which can cause the agent to access Gmail data without a clearly scoped user intent or explicit confirmation. Because this skill searches message metadata and snippets, over-triggering can expose sensitive email content in contexts where the user did not specifically authorize Gmail access.

Content

No source excerpt is available for this finding.