ClawHub
Back to skill

Security audit

JSON Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward local JSON formatting and query helper with no evidence of hidden network access, persistence, or destructive behavior.

Before installing, treat this as a local command-line JSON utility: it can read JSON files or stdin and can write an output file if asked. Review any data you pass through curl or stdin, especially secrets or private API responses, because the tool will print or write the selected JSON content as requested.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

External Script Fetching

High
Category
Supply Chain
Content
Pipe from curl:
```bash
curl -s https://api.example.com/data | python main.py - --query results.0
```

## Query Syntax
Confidence
90% confidence
Finding
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding
Shadow Command Trigger: 'format json' conflicts with built-in command 'format'

External Transmission

Medium
Category
Data Exfiltration
Content
Pipe from curl:
```bash
curl -s https://api.example.com/data | python main.py - --query results.0
```

## Query Syntax
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.