ClawHub

Skill Fin Report

Security checks across malware telemetry and agentic risk

Overview

This skill generates local A-share finance reports as described, with dependency and invocation cautions but no evidence of credential theft, trading actions, persistence, or exfiltration.

Install only if you are comfortable with public financial-data network requests, Python package installation, and local PDF generation. Prefer explicit stock-code invocations, review generated reports before sharing them, and keep WeasyPrint and related dependencies updated or pinned to vetted patched versions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares no permissions, yet its documented behavior clearly requires outbound network access to fetch market/news data and shell-like execution of local tools such as python3, pip3, and Ghostscript. This mismatch weakens platform trust boundaries and informed consent: an agent may invoke code with network and process-spawning capability that is not transparently declared, increasing risk if the implementation later expands or is abused.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases are very broad finance terms such as '金融报告', '投研报告', and '股票分析', which can match many ordinary user requests. That increases the chance of unintended auto-invocation, causing the skill to fetch external data and run local tooling when the user may not have intended to activate this specific capability.

Unpinned Dependencies

Low
Category
Supply Chain
Content
akshare>=1.10.0
pandas>=1.5.0
numpy>=1.23.0
weasyprint>=60.0
Confidence
95% confidence
Finding
akshare>=1.10.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
akshare>=1.10.0
pandas>=1.5.0
numpy>=1.23.0
weasyprint>=60.0
matplotlib>=3.7.0
Confidence
93% confidence
Finding
pandas>=1.5.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
akshare>=1.10.0
pandas>=1.5.0
numpy>=1.23.0
weasyprint>=60.0
matplotlib>=3.7.0
Confidence
93% confidence
Finding
numpy>=1.23.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
akshare>=1.10.0
pandas>=1.5.0
numpy>=1.23.0
weasyprint>=60.0
matplotlib>=3.7.0
Confidence
97% confidence
Finding
weasyprint>=60.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
pandas>=1.5.0
numpy>=1.23.0
weasyprint>=60.0
matplotlib>=3.7.0
Confidence
92% confidence
Finding
matplotlib>=3.7.0

Known Vulnerable Dependency: weasyprint — 2 advisory(ies): CVE-2024-28184 (WeasyPrint allows the attachment of arbitrary files and URLs to a PDF); CVE-2025-68616 (WeasyPrint has a Server-Side Request Forgery (SSRF) Protection Bypass via HTTP R)

High
Category
Supply Chain
Confidence
90% confidence
Finding
weasyprint

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal