ClawHub
Back to skill

Security audit

JSON解析器

Security checks for vulnerabilities and agentic risk

Overview

This JSON parsing skill asks for command execution and broad file/API capabilities that are not clearly scoped to its parsing purpose.

Review this skill carefully before installing. It may be suitable only if you intentionally want a JSON utility that can also write files, call APIs, and execute commands; otherwise prefer a parser that only reads input and writes explicitly requested outputs.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

High
Confidence
96% confidence
Finding
The skill is presented as a JSON parser/validator, but later advertises command execution capability, which is unnecessary and materially expands attack surface. In an agent environment, a parsing-oriented skill that can execute commands may be invoked under low suspicion and then used to run unintended system actions or pivot into broader host access.

Context-Inappropriate Capability

High
Confidence
98% confidence
Finding
Documenting system command execution for a local JSON parsing skill violates least privilege because parsing JSON does not inherently require shell access. This mismatch makes the skill more dangerous in context: users may trust it as a harmless data utility while it possesses capabilities that could modify files, inspect the environment, or run arbitrary host commands.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises file writing, API integration, and command execution without clear user-facing warnings about integrity, data exposure, or system impact. In combination with broad utility-style branding, this can mislead users into granting high-trust invocation to a skill that can alter the filesystem, transmit data, or affect the host environment.

Static analysis

No suspicious patterns detected.