ClawHub
Back to skill

Security audit

Jinn Node Tool Free

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed node-and-wallet worker tool, but it asks for broad execution authority around wallet, staking, credentials, and long-running task execution without tight enough scoping.

Review before installing. Use this only if you intentionally want an agent-assisted token worker node. Inspect the package scripts behind yarn setup, yarn worker, wallet backup, and staking before running them; use a dedicated low-balance wallet; avoid shared or CI machines; keep .env files and wallet backups out of logs and repositories; and limit any GitHub token to the minimum permissions needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Intent-Code Divergence

Medium
Confidence
85% confidence
Finding
The skill claims private keys are not uploaded, but it also documents wallet backup/export operations that package encrypted wallet material for output. Even if the key is encrypted, exporting it increases exfiltration risk through agent-visible files, logs, archives, or unsafe storage locations, making the assurance misleading.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The skill describes very broad capability coverage and generic scenario keywords, which can cause an agent to invoke it for loosely related requests beyond its intended node-management scope. In a skill with exec/write/read privileges, overbroad matching increases the chance of inappropriate command execution or handling of wallet-related operations in the wrong context.

Vague Triggers

Low
Confidence
75% confidence
Finding
The tags include broad terms such as writing, e-commerce, development, code, and automation that are not tightly scoped to a personal node-worker tool. This increases selection ambiguity and may cause the skill to activate in unrelated contexts, which is risky because the skill advertises command execution and file access.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.