ClawHub
Back to skill

Security audit

Json Beautifier Free

Security checks across malware telemetry and agentic risk

Overview

This is a simple JSON formatting skill with some broader-than-needed tool declarations, but no evidence of hidden, destructive, or data-exfiltrating behavior.

Before installing, treat this as a local JSON helper and grant only the permissions your agent actually needs. Be cautious with broad shell or write access, especially when processing untrusted JSON; prefer returning results in chat unless you explicitly ask it to write an output file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill declares exec capability even though its stated purpose is simple JSON formatting/validation, which should not require shell execution. Unnecessary command execution materially expands the attack surface: a prompt-injected or overly-permissive agent could run arbitrary local commands, access sensitive files, or pivot beyond the JSON-processing scope.

Description-Behavior Mismatch

Low
Confidence
88% confidence
Finding
The manifest includes write access despite the skill being described as a local formatter/validator with read-only style behavior. Unnecessary file-writing permissions can let an agent overwrite project files, alter configs, or persist malicious changes when handling untrusted JSON or instructions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.