ClawHub
Back to skill

Security audit

Skills of A-share performance data released by ft.tech.

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward financial-data lookup tool that runs bundled Python scripts to fetch disclosed market.ft.tech endpoints.

Install only if you are comfortable with the agent running the bundled Python scripts and making HTTPS GET requests to market.ft.tech for financial market data. No evidence was found of hidden persistence, credential collection, local data indexing, or destructive behavior.

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 instructs the agent to derive and execute a local Python entrypoint and explicitly states use of file path handling, shell execution, and network access, yet no permissions are declared. This creates a capability/permission mismatch that can bypass governance controls, making it harder for a host system or reviewer to understand and restrict what the skill is allowed to do.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.