ClawHub
Back to skill

Security audit

MintGarden

Security checks across malware telemetry and agentic risk

Overview

This MintGarden skill appears to be a read-only NFT lookup tool with some reliability and dependency hygiene issues, but no evidence of malicious behavior.

Before installing, understand that this appears safe for read-only MintGarden lookups, but collection event results may be broader than the command name suggests. Avoid using its event output alone for trading or due-diligence decisions, and prefer an updated release that pins and refreshes dependencies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The helper is named and documented as if it returns activity for a specific collection, but it ignores the supplied collectionId and delegates to a global events feed. This can mislead users or downstream agents into making decisions based on unrelated marketplace activity, creating an integrity issue in security- or finance-relevant workflows.

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The getEvents function accepts a collectionId parameter that implies scoped retrieval, but the implementation always fetches unfiltered global events and never uses the argument. This discrepancy can cause consumers to trust incorrect contextual data, which is dangerous when the skill is used for monitoring, due diligence, or trading-related decisions.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "Jeff Coleman",
  "license": "MIT",
  "dependencies": {
    "axios": "^1.6.0"
  },
  "engines": {
    "node": ">=18.0.0"
Confidence
96% confidence
Finding
"axios": "^1.6.0"

Known Vulnerable Dependency: axios==1.6.0 — 10 advisory(ies): CVE-2026-44494 (axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `co); CVE-2026-44495 (axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollut); CVE-2025-62718 (Axios has a NO_PROXY Hostname Normalization Bypass that Leads to SSRF) +7 more

High
Category
Supply Chain
Confidence
98% confidence
Finding
axios==1.6.0

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.