ClawHub
Back to skill

Security audit

Toon

Security checks across malware telemetry and agentic risk

Overview

This is a simple instruction-only skill for converting JSON to a compact format, with no evidence of hidden execution, exfiltration, or destructive behavior.

Before installing, verify the actual toon executable or @toon-format/cli package because the reviewed bundle does not include the helper script. Use the skill for token-saving transformations of trusted JSON, but avoid piping secrets, credentials, personal data, or outputs where exact raw JSON must be preserved.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill metadata describes the tool in very broad terms and suggests using it for any task outputting structured data. That can cause an agent to invoke an external transformer more often than necessary, increasing exposure of potentially sensitive API responses or file contents to an additional processing step and dependency.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The instruction to pipe any command output through `toon` is overly broad and lacks scope constraints. In an agent setting, this can normalize sending arbitrary command results through a Node-based CLI, which may process sensitive data and adds supply-chain and data-handling risk if used indiscriminately.

Vague Triggers

Medium
Confidence
95% confidence
Finding
Using absolute language like 'Always' encourages unconditional invocation whenever fetching APIs or reading JSON files. This is dangerous because many such payloads contain sensitive or regulated data, and the wording discourages contextual judgment about whether compression is necessary, safe, or policy-compliant.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.