ClawHub
Back to skill

Security audit

请求随机笑话

Security checks across malware telemetry and agentic risk

Overview

This skill only fetches random joke-style text from public web APIs and prints it, with no evidence of local data access, persistence, or hidden behavior.

Install only if you are comfortable with the skill contacting api.pearktrue.cn to retrieve jokes or quotes. Treat returned text as untrusted third-party content that may be inaccurate or inappropriate, and ensure the Python requests library is available before use.

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
95% confidence
Finding
The skill documentation describes a Python script that makes outbound requests to public APIs, but the skill declares no permissions. Undeclared network capability weakens review and policy enforcement because users and hosting platforms may not realize the skill can contact external services, exfiltrate prompts, or return untrusted remote content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.