ClawHub

Analyze Json Data

Security checks across malware telemetry and agentic risk

Overview

This skill appears to locally analyze JSON into an API spec, but its documentation unnecessarily mentions an API key without explaining any service.

Reasonable to install if you only need local JSON-to-OpenAPI help. Do not provide an API key or sensitive JSON until the publisher explains what service would receive it, because the current artifact does not need that key for its included script.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
83% confidence
Finding
The test recursively scans local files for secret-like patterns, which extends the skill’s access and inspection scope beyond its declared JSON/OpenAPI function. In an agent-skill context, unnecessary filesystem scanning can expose sensitive content in nearby files, logs, or test output and normalizes overbroad data access.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README marks an API_KEY as required but gives no disclosure that an external service may be contacted or that user JSON data could be transmitted off-host. For a skill that analyzes potentially sensitive JSON, this lack of transparency can lead to unintentional credential use and data exposure to third-party services.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation condition is broad: 'Analyze JSON data and generate a structured API design document or OpenAPI specification' does not clearly bound data sources, trust assumptions, or operational limits. Overly broad triggering can cause the skill to be invoked in unintended contexts, increasing the chance of processing sensitive data or being used where stronger validation and permission scoping are required.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal