ClawHub
Back to skill

Security audit

财经情报局

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed finance-news summarizer that may fetch public market news, run a local Python script, and save local cache/report files.

Install it if you want finance-news briefings and are comfortable with a local Python script contacting public finance websites and saving generated reports. Verify market-moving claims and do not make trades based only on its keyword-based sentiment or operation advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs the agent to create a local `finance-news/` directory for caches and reports, which is a file-write capability, but no corresponding permission is declared. Undeclared write access weakens sandboxing and user transparency, and could allow unexpected persistence of fetched content or generated reports beyond what a reviewer expects from the manifest.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger conditions are broad enough to activate on many ordinary finance-related conversations, including generic mentions of markets, stocks, industries, or investment briefings. Over-broad activation can cause the agent to invoke network-fetching and report-generation behavior unexpectedly, increasing the chance of unnecessary external access, unintended file creation, and user confusion about when the skill is being used.

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.