ClawHub
Back to skill

Security audit

FairScale Solana

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Solana wallet reputation skill, but it needs review because it can send wallet and transaction details to FairScale and may trigger paid wallet-backed calls without clear approval limits.

Install only if you intentionally want FairScale to process Solana wallet reputation checks. Require explicit user confirmation before sending wallet addresses, wallet lists, transaction amounts, or custom rules; store API keys as configured secrets rather than passing them on the command line; and do not enable wallet-funded x402 payments unless you have clear spending limits and per-call approval.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The README advertises broad plain-English prompts such as 'is this a bot?' and 'whale?' without defining strict trigger boundaries or requiring explicit skill selection. In agent ecosystems that auto-route based on natural language, this can cause unintended invocation during ordinary conversation, leading to unnecessary external requests, data disclosure of wallet addresses, or unintended paid calls.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The usage section includes vague standalone prompts like 'Is this a bot?' and 'Diamond hands?' that are common conversational phrases rather than uniquely scoped commands. In systems with automatic tool selection, these examples increase the chance of accidental activation, which is especially relevant here because the skill may transmit wallet data to a third-party service and may incur per-call charges via x402.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs agents to send wallet addresses and transaction amount data to a third-party API, but it does not disclose that this information leaves the local trust boundary or explain the associated privacy, profiling, and operational risks. In this context, wallet addresses are sensitive financial identifiers, and combining them with transaction intent/amount can expose user behavior to an external service without informed consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.