ClawHub
Back to skill

Security audit

A Share Event

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed A-share event-analysis skill that uses public web and market data, with no hidden access or account-changing behavior found.

Install this if you want A-share announcement and policy impact analysis. Before relying on outputs, verify key claims against official announcements or policy documents, and make sure the separate cn-stock-data helper on your machine comes from a trusted source.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list is very broad and includes many generic finance phrases such as '公告分析', '利好还是利空', and 'event analysis', plus a 'MUST USE' directive. This can cause unintended invocation on ambiguous user requests, routing users into a workflow that performs market-impact analysis and web/data lookups without clear user intent, which increases the chance of incorrect task selection and over-collection of external context.

Natural-Language Policy Violations

Low
Confidence
80% confidence
Finding
The skill is explicitly framed around A-share analysis and Chinese-language trigger phrases, with no clear opt-in or fallback behavior for users operating in other languages or markets. This can misroute non-Chinese or non-A-share requests into a locale-specific workflow, leading to misleading analysis, irrelevant data retrieval, or user confusion rather than direct system compromise.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.