ClawHub
Back to skill

Security audit

SkillMarket

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed marketplace helper that fetches skill listings and install instructions from Zerone, with installation gated on user approval.

Install only if you want your agent to contact Zerone's marketplace and potentially add skills under `.agent/skills/`. Review any fetched install commands and the target skill before approving them, because third-party marketplace content can change and installed skills persist.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to access a remote marketplace API and fetch installation instructions, but it does not declare corresponding permissions. Undeclared network capability undermines transparency and permission gating, making it easier for a user or runtime to invoke external communications without clear review.

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger includes broad phrases like 'add a skill', 'install a skill', and 'browse skills', plus mentions of any non-installed skill name. This can cause unintended activation in ordinary conversation, leading the agent into a workflow that performs network lookups and prepares installation steps from an external source.

External Transmission

Medium
Category
Data Exfiltration
Content
---
name: skill-market
description: Use this skill to find, explore, and install new skills from the Zerone Skill Market (https://api.zerone.market/api). Trigger this when the user asks to "add a skill", "install a skill", "browse skills", or mentions a skill name that is not currently installed.
---

# Skill Market
Confidence
88% confidence
Finding
https://api.zerone.market/

External Transmission

Medium
Category
Data Exfiltration
Content
Only after explicit user approval, execute the instructions to install the skill into the `.agent/skills/` directory.

## Current Environment Context
- **Market Endpoint:** `https://api.zerone.market/api`
- **Default Language:** `en` (English is used for API requests as per instructions)
- **Local Skills path:** `.agent/skills/`
Confidence
86% confidence
Finding
https://api.zerone.market/

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.