ClawHub
Back to skill

Security audit

财经日报

Security checks across malware telemetry and agentic risk

Overview

This skill coherently generates a finance-market HTML report using public market-data sources, with no evidence of credential access, hidden exfiltration, destructive behavior, or persistence beyond generated files and installed dependencies.

Install this if you want an agent to fetch public finance data and create local HTML reports. Be aware it may install Python packages, contact market-data providers through AKShare, and load Chart.js from a CDN when the report is opened; use a virtual environment and review the generated HTML if you need strict dependency or network control.

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
88% confidence
Finding
The trigger conditions are broad enough to match many ordinary finance-related requests such as market overviews or daily summaries, which can cause the skill to activate unexpectedly. Over-broad activation increases the chance that code execution, network retrieval, and file generation occur in contexts where the user did not specifically intend to run this particular skill.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The manifest description advertises many generic trigger phrases like '今日财经' and '股市行情' that are common user queries, making accidental or competing activation more likely. In this skill's context, accidental activation is more concerning because the workflow includes package installation, network access, and HTML file creation rather than a purely conversational response.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.