Analyze Json Data

• Outcome: Review
• Latest audit: May 28, 2026 · 11:23 AM UTC
• Version: 1.0.1

Overview

This looks like a local JSON-to-OpenAPI helper, but it asks for an unexplained API key that does not fit the visible implementation.

Review before installing. Use only JSON files you intend to analyze, choose output paths deliberately, and do not provide an API key unless the publisher documents the service, why the credential is needed, and whether any JSON data is transmitted off-host.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 84% confidence
• Finding: The skill appears capable of file read/write behavior but does not declare any permissions or boundaries for that access. Undeclared capabilities reduce transparency and can enable the skill to access or modify local data unexpectedly, which is risky even if the markdown only describes behavior rather than executable code.

Intent-Code Divergence

Medium

• Confidence: 83% confidence
• Finding: The README documents separate read and write modes even though the stated purpose is JSON analysis and OpenAPI/API document generation, creating a capability mismatch. That ambiguity can mislead users into invoking file-modifying behavior they did not expect, which increases the risk of unintended data changes or hidden side effects in an analysis-oriented skill.

Context-Inappropriate Capability

Medium

• Confidence: 86% confidence
• Finding: Requesting an API_KEY for a skill whose described function is local JSON analysis is suspicious because it implies undeclared external service usage. This can expose sensitive input data or credentials to remote systems without clear user understanding, especially when the README does not justify why network access is necessary.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: Describing a write mode without warning that it may modify files or data undermines informed consent and safe operation. In a skill positioned as a JSON analysis tool, undocumented write behavior is more concerning because users may reasonably expect read-only processing and could unintentionally overwrite or alter data.

Missing User Warnings

Low

• Confidence: 81% confidence
• Finding: Asking for an API key without explaining privacy or network transmission implications can cause users to provide credentials and sensitive JSON data without understanding where that information goes. While the README alone does not prove exfiltration, the omission meaningfully increases risk because the skill's purpose does not obviously require remote processing.

Vague Triggers

Medium

• Confidence: 77% confidence
• Finding: The trigger condition is broad and underspecified, so the skill may activate in situations outside its intended use. Overbroad activation can cause the agent to process unintended JSON content, generate misleading output, or invoke capabilities when a safer or more appropriate skill should have been used.

Static analysis

No suspicious patterns detected.