ClawHub
Back to skill

Security audit

fund-tracker

Security checks across malware telemetry and agentic risk

Overview

This is a fund-status checker that fetches public fund data and keeps local history, with no evidence of hidden trading, credential use, or unrelated access.

Install only if you are comfortable with a Python dependency stack that queries AKShare/Eastmoney and stores local fund-check history inside the skill directory. Treat the results as informational, not financial advice.

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
91% confidence
Finding
The skill instructs the agent to run local Python code and to update local JSON/history files, which implies file read/write capability, but the manifest declares only a required binary and no corresponding permissions. This creates a permission-model mismatch: users or hosting platforms may believe the skill is less capable than it actually is, reducing transparency and weakening security review and consent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.