ClawHub
Back to skill

Security audit

Office Automation Test

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese office-document drafting skill with no code execution, persistence, credentials, or external data access.

Install this if you want a Chinese-language helper for drafting routine workplace reports and meeting notes. Be mindful that the generated documents may include business-sensitive information you provide, but the artifact itself does not show external sharing or privileged access.

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
93% confidence
Finding

The activation logic relies on broad natural-language phrases such as ‘写日报’, ‘生成周报’, and ‘整理会议纪要’, which are common in ordinary conversation and can easily appear in messages where the user is not intentionally invoking the skill. This can cause unintended activation, leading the agent to collect or generate workplace documents in the wrong context and potentially process sensitive business information without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The skill name, description, instructions, and examples are all presented only in Chinese, and line 22 mentions users may adjust language style but does not explicitly offer language or locale selection. This can be interpreted as forcing a specific language by default without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.