ClawHub
Back to skill

Security audit

Graph Advocate

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed blockchain data routing skill that sends user queries to a remote service and has optional paid wallet-based endpoints, with no local code execution or hidden persistence found.

Install only if you are comfortable sending blockchain questions, wallet addresses, and trading intent to graphadvocate.com. Start without a wallet; if enabling x402 paid endpoints, use interactive per-call approval, a low-balance wallet, and spend caps.

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 description invites routing of 'any blockchain question in plain English' and enumerates a very wide range of domains, which makes invocation boundaries vague and increases the chance the agent will trigger this skill for loosely related prompts. In a tool that connects to a remote endpoint and can route data requests, overly broad activation can cause unintended external data disclosure, misrouting, or unnecessary tool use driven by ambiguous everyday language.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/subgraph-registry.md:8

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:87