ClawHub
Back to skill

Security audit

yanlin-company-filings

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrowly scoped public company-announcement collector that discloses its data sources and does not show credential access, persistence, or destructive behavior.

Before installing, understand that running the skill contacts public Chinese financial-information websites to retrieve market/news data. It does not appear to access local secrets, modify files, or run in the background, but a manifest-level network allowlist would make its outbound access clearer.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly documents external data collection from multiple internet sources and a Python fetch script, but it does not declare any corresponding network permission. Undeclared network access weakens reviewability and consent boundaries, making it easier for a skill to exfiltrate data, contact unexpected endpoints, or bypass platform policy checks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.