ClawHub
Back to skill

Security audit

Market Structure Scan

Security checks across malware telemetry and agentic risk

Overview

This skill is a public market-analysis helper and the reviewed artifacts do not show credential use, persistence, destructive actions, or hidden behavior.

Install this only if you want the agent to browse public market-data sites and generate informational technical-analysis summaries. Use explicit tickers or coin slugs to avoid accidental activation, and do not treat the output as financial or trading advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list includes very generic phrases such as "scan market," "market scan," "full scan," and asset-only variants like "scan ETH" that can match ordinary user requests and unintentionally invoke this skill. In an agent environment, broad trigger collisions can cause the wrong skill to run, leading to misleading financial analysis, unexpected web access, and reduced user control over which capability is activated.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.