ClawHub
Back to skill

Security audit

Volcengine Knowledge Search

Security checks across malware telemetry and agentic risk

Overview

This is a focused Volcengine documentation search skill with disclosed network use and limited temporary file output.

Install if you want an agent to look up public Volcengine documentation. Be aware that search terms and document URLs are sent to Volcengine's documentation service, and long results can be saved temporarily on disk for the agent to read.

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 invokes Python with network access, can write files, reads environment-controlled settings, and relies on shell execution, but it declares no explicit permissions boundary. That mismatch can cause the host or reviewer to underestimate the skill's capabilities, making outbound requests and local file output occur without clear user or platform consent. In this context the behavior is partly expected for a documentation-fetching skill, but the lack of declaration still weakens security review and containment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.