Security audit

JSON Diff Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent static JSON comparison helper, with the main caution that users should not paste confidential JSON into hosted copies of the tool.

Install/use is reasonable for non-sensitive JSON comparisons. Prefer the bundled/local version or the stable ClawHub/GitHub source, and do not paste secrets, tokens, customer records, or production payloads into externally hosted copies, especially the temporary trycloudflare URL.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The instruction to invoke the skill whenever a user asks for JSON comparison is broader than the enumerated trigger phrases and can cause over-activation on ambiguous requests. This may route users to an external tool unnecessarily, increasing the chance that unrelated or sensitive JSON is exposed to third-party infrastructure without clear user intent.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill directs users to external URLs where they are expected to paste JSON, but it provides no warning against using secrets, production data, tokens, customer records, or other confidential content. Even though the page claims local processing, the endpoints are externally hosted and one uses a temporary trycloudflare domain, so users may be induced to trust an unvetted service with sensitive data.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The document declares `lang="zh-CN"`, and all visible interface text is presented only in Simplified Chinese. Under the policy, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: The primary skill description is written in Chinese and does not indicate that other languages are available or that the language is user-selectable. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: Most of the descriptive and instructional text is written in Chinese, and the file does not indicate that other languages are supported or that Chinese is an intentional locale-specific constraint. This can conflict with a language-choice policy when users are not given an explicit option.

Static analysis

No suspicious patterns detected.