ClawHub
Back to skill

Security audit

Json Parse Engine Free

Security checks across malware telemetry and agentic risk

Overview

This appears to be a local JSON utility, but it asks for file-writing and command-running authority that is not clearly scoped or needed.

Install only if you are comfortable giving this skill local read and command-execution access, and treat the declared write permission as unnecessary unless the publisher adds clear output-saving behavior and scope limits. Use it on trusted, user-selected JSON files and avoid pointing it at directories or files containing secrets.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (3)

Scope Creep

Medium
Confidence
95% confidence
Finding
The manifest grants `write` capability even though the skill is described as a local JSON parsing, flattening, extraction, and validation tool. This creates unnecessary privilege that could let the skill modify files if invoked through an agent, expanding the blast radius well beyond its stated purpose.

Intent-Code Divergence

Low
Confidence
73% confidence
Finding
The documentation says the free version does not support batch parsing or directory scanning, but the skill still advertises broad `read` access with no technical constraints. In an agent environment, that mismatch can enable unintended reading of arbitrary local files or directories, especially if the agent interprets user prompts broadly.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill exposes `write` and `exec` capabilities without warning users that it can alter files or run commands on the host. In an agent setting, undisclosed powerful capabilities increase the chance of unsafe execution, misuse, or social-engineering-driven actions that exceed the user's expectation of a simple JSON utility.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.