ClawHub
Back to skill

Security audit

Investment Checklist | 投资决策清单

Security checks for vulnerabilities and agentic risk

Overview

This is a visible markdown-only investment checklist, but users should not treat its buy/sell scoring as professional financial advice.

Install only if you want a Chinese-language investing checklist. Treat the scoring and buy/sell wording as personal decision support, not professional financial, legal, or tax advice, and verify important decisions independently before acting.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (4)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill lacks a clear warning that its outputs are not financial advice, despite being designed to influence buy, hold, and sell decisions. In this context, omission of that disclaimer materially increases the chance that users treat the skill as authoritative guidance and act on it in ways that could cause significant financial loss.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill description, instructions, and command examples are entirely in Chinese, which implicitly constrains interaction to a specific language. The file does not offer a language choice, ask for user preference, or explain that the skill is intentionally limited to a Chinese-speaking context.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are broad and natural, so the skill may activate during ordinary investment conversation and steer the interaction into structured buy/sell guidance unexpectedly. In a finance context, accidental invocation is more dangerous because it can shape real monetary decisions without the user's explicit intent to seek formalized investment recommendations.

Description-Behavior Mismatch

Low
Confidence
87% confidence
Finding
The skill is presented as a decision-support checklist, but the scoring table and explicit thresholds such as '8-10分：强烈推荐买入' turn it into prescriptive investment advice. That can materially influence trading decisions without any suitability checks, uncertainty disclosure, or regulatory framing, increasing the risk of financial harm if users over-rely on the output.

Static analysis

No suspicious patterns detected.