ClawHub

虾皮SQL自由选股

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a stock-screening helper, and the only reported issue is imprecise activation wording rather than unsafe behavior.

Safe to install if you want SQL-style stock screening assistance. Be aware it may activate on broad investing or stock-screening questions, so prefer using it only when you explicitly want SQL-like conditional screening and verify any financial outputs independently.

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
94% confidence
Finding
The trigger list includes very broad terms such as '选股' and '股票筛选', which are likely to appear in many ordinary finance conversations and can cause the skill to activate when the user did not specifically request this SQL-based tool. Over-broad activation increases the chance the agent will route users into a tool that may prompt token setup, CLI usage, or SQL-style query construction unnecessarily, creating unintended tool use and possible exposure of sensitive workflow details.

Vague Triggers

Low
Confidence
87% confidence
Finding
The activation guidance mixes broad scenarios like general stock screening and quantitative filtering with narrower SQL-specific use cases, but the boundary against ordinary stock-analysis requests is not strict enough. This ambiguity can lead to accidental invocation, reducing routing precision and causing the agent to use a more powerful or irrelevant skill than intended.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal