ClawHub
Back to skill

Security audit

Agent Code No.7 Commander

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language task-orchestration skill for office, legal, finance, tax, research, and due-diligence assistance, with no executable code or hidden system access.

Installers should treat this as a Chinese-language professional-assistance skill. Avoid sharing unnecessary sensitive business, legal, tax, or financial data, and treat its outputs as drafts or research support rather than a substitute for licensed professional advice.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The entire skill description and system prompt are written as Chinese-only operating instructions, with no indication that the user may choose another language. That creates a locale/language policy issue because the skill appears to impose a specific language without opt-in or a documented region-specific requirement.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill can be activated by essentially any natural-language request, which makes its scope overly broad and increases the chance of unintended routing, misuse, or handling of tasks beyond its intended trust boundaries. Because this is a commander/orchestrator skill that delegates across legal, financial, tax, research, and due-diligence domains, overly general activation materially raises the risk of inappropriate invocation and unsafe task delegation.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The manifest description is written entirely in Chinese, which can impose a locale/language constraint on users without indicating any option for other languages. Under the policy, language-specific skill metadata should either offer user choice or clearly justify the locale restriction.

Static analysis

No suspicious patterns detected.