ClawHub
Back to skill

Security audit

Stock Screener

Security checks for vulnerabilities and agentic risk

Overview

This is a stock-screening reference skill with no executable code, persistence, credential access, or hidden behavior, though users should treat outputs as informational financial analysis only.

Install only if you want a Chinese-language A-share and Hong Kong stock screening helper. Treat its scores and recommendation labels as informational screening output, verify data independently, and do not rely on it as personalized investment advice or trading authorization.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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 (5)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Content
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: "00000000000000000000000000000000"
    PropagateID: "00000000000000000000000000000000"
    ReservedCode1: 304402206d3208f2e96978ccbd5b6af7b25be62874f7edf36c16799f96a0fc821160bce002201c87d33621e328137f8c5ba6757d46de93c2b519e2100b187a569d90fb6dd9aa
    ReservedCode2: 30450220137f0aba1e50cf8984d08ac383b1b1d4aff013a3a9c4acc1a1b4eeeb3c364536022100b062a65ed9defeff4098b1bfc7eb21919e5ed3d82e49b4178a5b666c70f6b970
description: 基于技术面、资金面、基本面三维度筛选A股和港股符合条件的股票。支持多因子选股、条件过滤、排序输出。
name: stock-screener
---

# Stock Screener - 智能选股器

## 功能概述

根据用户指定的条件，从A股（上海/深圳交易
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Vague Triggers

Medium
Confidence
93% confidence
Finding
The activation guidance is overly broad: phrases like '选股', '筛选股票', and '条件选股' can match many ordinary finance conversations without clear scoping or disambiguation. That can cause unintended invocation of the skill, increasing the chance of irrelevant tool use, misleading financial output, or routing users into an investment-oriented workflow they did not explicitly request.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrase "帮我找" is overly broad and can match many normal user requests unrelated to stock screening, causing the skill to activate outside its intended scope. In an agent system, broad trigger overlap can lead to incorrect routing, unintended data exposure to the skill, or invocation in contexts where financial logic is inappropriate.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The document provides concrete stock-screening criteria, scoring thresholds, and recommendation labels such as 'strongly recommend' and 'recommended' without any disclaimer that the content is informational rather than investment advice. In a financial-decision context, users may reasonably rely on these outputs for trading, creating risk of unsuitable or harmful financial decisions and possible compliance issues.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The natural-language content, headings, labels, and instructions are presented exclusively in Chinese, which can amount to a language/locale constraint when no opt-in or alternative is documented. SQP-3 applies to all file types and covers cases where a skill effectively forces a specific language without user choice.

Static analysis

No suspicious patterns detected.