ClawHub
Back to skill

Security audit

Email Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only email assistance skill that asks users to provide email content and does not try to access, send, or delete email itself.

Installers should understand that email content can be sensitive; use this skill with email text you intentionally provide, review generated replies before sending, and do not assume it can safely operate on a live inbox without additional permission controls.

A.I.G

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

SkillSpector

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill's activation guidance is framed as broad, everyday situations like being busy with email or wanting quick understanding, rather than narrow, explicit invocation criteria. This can cause unintended triggering in normal conversation, leading the assistant to process email-related content when the user may not have explicitly chosen to invoke this skill, which is risky because email content often contains sensitive business or personal information.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example inputs use highly generic phrases such as '帮我处理这封邮件' and '帮我看看今天收到的邮件', which are common natural-language requests and may overlap with ordinary conversation. If the platform uses semantic or pattern-based routing, these broad triggers increase the chance of accidental invocation and unintended handling or summarization of potentially sensitive mailbox content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.