ClawHub
Back to skill

Security audit

a-stock-trading-software

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Chinese A-share trading software guide, but it includes automatic buy/sell condition-order examples without enough safety boundaries for live trading.

Review this skill carefully before installing. It appears to be a non-executable trading software guide, but users should treat the condition-order examples as risky live-trading automation, verify broker rules, avoid treating the sample prices as advice, and require explicit confirmation before using any automatic order feature.

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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill describes automatic buy and sell condition orders such as buying above 20 yuan and selling below 18 yuan, but provides no warning about automatic execution, order-routing risks, slippage, misconfiguration, or financial loss. Because this is directly tied to live securities trading, the absence of risk disclosures and safety checks makes the content materially more dangerous than generic software tips.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description and instructions are entirely in Chinese and targeted at A-share trading, but the file does not explicitly state that the skill is region/language-specific or offer an opt-in language choice. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are generic everyday questions such as how to quickly view the market or what shortcuts exist, without clear scoping to a specific trading platform, user intent, or safety boundaries. In a trading context, overly broad triggers can cause the skill to activate in situations the user did not clearly intend, increasing the chance of unsolicited operational guidance that may influence live trading behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.