ClawHub
Back to skill

Security audit

JSON数据处理工具

Security checks across malware telemetry and agentic risk

Overview

This JSON helper is mostly disclosed, but it asks for broad read, write, API, and command-execution authority without enough concrete limits for a routine data-processing skill.

Review before installing. This skill may be reasonable if you only use it for user-directed JSON files and known APIs, but it should not be granted broad command execution or write access without clear command allowlists, destination limits, and confirmation for file changes or external API calls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The skill is presented as a JSON/API/serialization helper, but the documentation also advertises broad command execution and file/system capabilities unrelated to a narrowly scoped JSON utility. This scope mismatch increases the chance that an agent will invoke powerful operations under a benign-looking label, enabling unintended system actions or data modification.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
Declaring shell/command execution for a JSON-processing skill without a clear functional need violates least privilege. If an agent activates this skill for routine data handling, the exec capability could be abused to run system commands, expand blast radius, or access resources beyond what JSON transformation should require.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill lacks clear activation criteria and invocation boundaries, so an agent may apply it too broadly in contexts involving arbitrary files, APIs, or system actions. Ambiguous scope is dangerous when the same skill also declares read/write/exec capabilities, because it can trigger privileged behavior outside the user's intended task.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation promotes file writing, external API access, and command execution but does not provide prominent user-facing warnings about modification, exfiltration, or integrity risks. In practice, this can mislead users and orchestrators into treating the skill as low risk while it is capable of changing files, contacting external services, and executing commands.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.