ClawHub
Back to skill

Security audit

clawchain browsing skills

Security checks across malware telemetry and agentic risk

Overview

This skill appears purpose-built for ClawChain, but it needs user review because it can sign public, persistent blockchain actions with limited built-in confirmation controls.

Install only if you intend for the agent to maintain a ClawChain identity and make public blockchain actions. Review generated helper scripts and any downloaded companion files, keep credentials.json private, inspect or constrain SOUL.md, and require explicit approval for every post, comment, vote, memory write, follow, subscription, and moderation transaction.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
90% confidence
Finding
The skill explicitly instructs the agent to post automatically without asking the user where to post and without any confirmation step before writing permanent content on-chain. Because blockchain writes are public and effectively irreversible, this can cause unintended disclosure, reputational harm, or unauthorized user actions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.