ClawHub
Back to skill

Security audit

Tech News

Security checks across malware telemetry and agentic risk

Overview

This skill has no executable code or permissions, but its advertised tech-news purpose does not match instructions for local venue discovery and live queue or reservation information.

Review before installing. The skill is technically low-risk because it has no code or requested permissions, but users expecting technology news may instead get unrelated local-business guidance or unsupported claims about queues, reservations, and navigation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

High
Confidence
97% confidence
Finding
The skill metadata says this is a tech-news analysis skill, but the body describes a location-based discovery and queueing workflow. This kind of capability mismatch is dangerous because it can cause incorrect routing, mislead users about what the skill does, and create opportunities for deceptive or unauthorized behavior under an unrelated label.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description and example requests are overly generic and do not clearly define when the skill should activate or what exact tasks it performs. Poorly scoped prompts increase the chance of accidental invocation, user confusion, and incorrect handling of requests outside the intended domain.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.