ClawHub
Back to skill

Security audit

yanlin-news-filter

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public finance news from a disclosed source and filters it locally, with no evidence of hidden data access, persistence, or destructive behavior.

Before installing, understand that the skill makes outbound requests to Sina Finance to retrieve current news. Its filtering is keyword-based and may miss or mis-rank events, and the documented date argument is not implemented, but no hidden or high-impact behavior was found.

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
89% confidence
Finding
The skill explicitly describes fetching news from public financial information sources and provides a script entrypoint that implies outbound network access, but no permissions are declared. Undeclared network capability undermines transparency and reviewability, and could allow the skill to contact unintended endpoints or exfiltrate data if the backing script is modified or abused.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.