ClawHub

全方位智能股票分析v4

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese stock-analysis skill that gathers market data and gives trading-oriented analysis, with no evidence of hidden execution, persistence, account access, or destructive behavior.

Install this only if you want Chinese-language stock analysis and are comfortable with stock symbols, company names, and related searches being sent to external market-data/search providers. Keep ~/Desktop/股票知识库/ free of secrets or unrelated private material, set TUSHARE_TOKEN only when you intend to use Tushare data, and treat any buy/sell guidance as informational rather than personalized financial advice.

SkillSpector

By NVIDIA
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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger examples are broad and match ordinary stock-related conversation, which can cause the skill to activate in situations where the user did not explicitly request this specialized analysis workflow. In a finance context, unintended invocation is more serious because the skill produces concrete trading-oriented recommendations, increasing the risk of unsolicited or misplaced financial guidance.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The manifest description is very broad and promises automatic buy/sell advice across A-shares, Hong Kong stocks, U.S. stocks, and ETFs without clearly constraining when the skill should activate. Broad activation scope increases the chance the agent is invoked in unintended contexts, which can expose users to unrequested financial guidance or trigger risky data access paths tied to stock-related prompts.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The manifest hard-codes the skill to zh-CN without indicating that this restriction is intentional or user-selectable. This can cause the skill to activate for users who do not expect Chinese-only behavior, increasing the risk of misunderstandings in financial advice and making consent and usability controls weaker.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal