ClawHub
Back to skill

Security audit

Wojak.ink - NFT Browser

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent NFT market browser that uses public marketplace APIs and scoped local JSON history files, with no evidence of hidden access, credential use, wallet control, or destructive behavior.

Install only if you are comfortable with a Node CLI contacting MintGarden, Dexie, and IPFS image gateways and keeping local market-history JSON files. Delete the skill's data directory if you do not want retained history, and review npm dependencies as you would for any third-party package.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Low
Confidence
93% confidence
Finding
The feature description states that historical price and sales data are stored locally, but it does not clearly warn users about the persistence, retention period, and local privacy implications of that storage. While the data described is market data rather than obvious personal secrets, undocumented local persistence can still surprise users, create unnecessary disk artifacts, and expose usage history or operational context on shared systems.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill advertises broad natural-language triggering for any user asking about Wojak NFTs or marketplace data, which can cause unintended invocation and external lookups without an explicit command. In chat environments, this increases the chance of accidental activation, unnecessary data transmission to third-party APIs, and surprising behavior for users who did not intend to invoke the skill.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The skill describes use of external APIs and historical data storage but does not clearly warn users that their queries may be sent to third-party services or that market data may be retained. This is primarily a transparency and privacy issue: users may unknowingly trigger outbound requests or persistent tracking features.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "Jeff Coleman",
  "license": "MIT",
  "dependencies": {
    "node-fetch": "^2.6.7"
  }
}
Confidence
89% confidence
Finding
The dependency is specified with a caret range (^2.6.7), which allows automatic installation of newer compatible versions within the major release line. This can introduce supply-chain risk if a newly published version is compromised or contains a security regression, though the package itself is common and nothing else in this file suggests malicious intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.