ClawHub
Back to skill

Security audit

Email Business Zh

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese business email drafting skill with no hidden execution, network access, persistence, or credential handling.

Install this when you want help drafting formal Chinese business emails. Check the final message before sending, especially recipient names, dates, commitments, and tone, and avoid invoking it for non-Chinese or non-business email tasks unless that is intentional.

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
  • 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)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill is explicitly scoped to Chinese output and does not indicate any user choice, fallback, or confirmation when the user's preferred language may differ. While not a direct security exploit, this can create unsafe mismatches in business communication, including misunderstanding, accidental disclosure through mistranslation workflows, or sending inappropriate-language content in professional contexts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases are broad and include common terms such as 'email写作' and '邮件撰写', which can match ordinary user requests outside a narrowly scoped business-email workflow. This can cause unintended invocation of the skill, leading to incorrect routing, user surprise, or the skill taking over requests that should remain general-purpose or be handled by a different, safer skill.

Static analysis

No suspicious patterns detected.