ClawHub
Back to skill

Security audit

Slv Rpc

Security checks across malware telemetry and agentic risk

Overview

The skill is for legitimate Solana RPC server administration, but it asks agents to run high-impact remote playbooks whose actual contents are not included in the package.

Review this before installing. Use it only if you trust the SLV/ValidatorsDAO toolchain and can inspect the exact ~/.slv/template Ansible playbooks that will run. Limit inventory targets, run Ansible check mode first, confirm any service restarts, ledger deletion, disk formatting, firewall changes, or key-copying steps, and avoid pasting private keys or API secrets into the agent chat.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README prominently describes deploying, configuring, and managing Solana RPC nodes, including lifecycle operations and source builds, but does not warn that these actions are system-changing and can affect availability, data integrity, cost, and security of remote servers. In an agent-skill context, this omission increases the chance that an AI agent or user invokes destructive or high-impact operations without explicit confirmation or understanding of the consequences.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.generated_source_template_injection

User-controlled placeholder is embedded directly into generated source code.

Critical
Code
suspicious.generated_source_template_injection
Location
AGENT.md:195