ClawHub
Back to skill

Security audit

胡田 OPC导师 一人公司财税规划

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Chinese-language tax-planning guidance skill with no code, tool access, persistence, or hidden data handling.

Before installing, users should treat this as general China-oriented tax-planning guidance and verify current tax thresholds, filing rules, and entity choices with a qualified professional for their jurisdiction.

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 trigger conditions are broad enough to match many ordinary business, startup, or tax-related conversations, which can cause the skill to activate outside its intended scope. In a finance and tax-planning context, unintended invocation matters because users may receive jurisdiction-specific or entity-structure advice without clear qualification, increasing the risk of misleading guidance and compliance mistakes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill's natural-language instructions and outputs are entirely Chinese, which can effectively force a specific language experience if used in a broader multilingual environment. No opt-in, fallback language behavior, or justification for a Chinese-only locale is documented in the file.

Content

No source excerpt is available for this finding.