Security audit

场外基金查询

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward fund lookup tool that contacts public fund-data APIs and does not show hidden persistence, credential access, or destructive behavior.

Install only if you are comfortable with the tool sending fund codes you query to public Eastmoney/Tiantian fund API endpoints. The metadata should ideally declare network access more explicitly, but the behavior is disclosed and proportionate to the skill's purpose.

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: 93% confidence
Finding: The skill explicitly relies on an external public API (`fund.eastmoney.com`) and therefore has network capability, but the metadata declares only a local binary requirement and no corresponding permission. Undeclared network access reduces transparency and can bypass policy or review expectations, creating risk around data exfiltration, dependency on untrusted remote content, and unexpected outbound requests.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal