ClawHub
Back to skill

Security audit

TrencherAI — Base Chain Intelligence

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill clearly describes a paid Base-chain token scoring API and its wallet-based x402 payment behavior, but users should control spending before use.

Install only if you intend to let an x402-compatible client make paid USDC requests. Use a low-balance or dedicated wallet, enable per-call confirmation or strict spending limits, verify the pay-to address, and avoid letting automated trading act solely on these scores.

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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill describes paid endpoints and says an x402-compatible client will pay automatically, but it does not present a prominent upfront warning that invoking requests can trigger real on-chain USDC payments from the user's wallet. In an agent setting, this omission can cause unintended spending because users may treat the skill like a normal read-only API integration rather than a transaction-capable action.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal