ClawHub
Back to skill

Security audit

opennews

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward helper for querying a disclosed crypto-news API, with expected third-party data sharing but no hidden execution or persistence.

Install only if you trust the OpenNews/6551 service. Treat OPENNEWS_TOKEN like an API key, avoid putting secrets or sensitive personal data in search terms, and treat AI ratings or trading signals as informational rather than financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Low
Confidence
94% confidence
Finding
The skill instructs users to send authenticated requests and likely user-supplied queries to a third-party service, but it does not clearly warn that prompts, search terms, request metadata, and the bearer token are transmitted off-platform. This is a real transparency/privacy issue because users may assume the skill operates locally or may not realize their inputs are disclosed to an external provider.

External Transmission

Medium
Category
Data Exfiltration
Content
env:
        - OPENNEWS_TOKEN
      bins:
        - curl
    primaryEnv: OPENNEWS_TOKEN
    emoji: "\U0001F4F0"
    install:
Confidence
92% confidence
Finding
The skill is explicitly designed to transmit data and an API bearer token to an external service using curl. In context this is expected functionality, but it is still a true external-transmission risk because any user query, filtering criteria, and authentication material leave the local environment and go to a third-party endpoint.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.