ClawHub
Back to skill

Security audit

Stock Top Gainers

Security checks across malware telemetry and agentic risk

Overview

This stock-ranking skill is purpose-aligned and disclosed, with the main caveat that it can return stale cached market data if live fetching fails.

Install only if you are comfortable with the skill using Python and the OpenClaw browser tool to visit public stock-data sites. Check whether results came from live browsing or the dated cached sample before relying on them, and treat the output as informational rather than investment advice.

SkillSpector

By NVIDIA
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 (2)

Intent-Code Divergence

Medium
Confidence
85% confidence
Finding
The module documentation explicitly claims that data date validation was added, but the implementation returns browser and cached results without verifying freshness. In a stock-ranking skill, stale or mislabeled market data can mislead downstream decisions and create integrity risk, especially because the cache file is date-stamped but never checked against current expectations.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad finance-related requests such as '股票排行榜' and '最近哪些股票涨得好', which can cause the skill to activate for loosely related user intents. Overbroad activation can route user requests to an unintended skill, causing unnecessary external browsing and potentially incorrect or undesired financial outputs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.