ClawHub
Back to skill

Security audit

Axodus Trading Integration

Security checks across malware telemetry and agentic risk

Overview

This is a trading-integration checklist with clear paper-mode and risk-control guidance, though its trigger metadata is malformed.

Reasonable to install as guidance, but fix or review the trigger metadata before relying on automatic activation. Do not connect real accounts until paper-mode tests, explicit live-mode confirmation, risk limits, audit logs, and secure secret storage are in place.

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
90% confidence
Finding
The trigger definition is effectively unspecified and appears serialized as a generic object array, which makes activation behavior unclear and potentially overly broad. In a trading-integration skill, ambiguous triggering is more dangerous because unintended invocation could connect or act on trading-related infrastructure without clear user intent or sufficient guardrails.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.