ClawHub
Back to skill

Security audit

AI 工作工具

Security checks across malware telemetry and agentic risk

Overview

The skill matches its stated task-marketplace purpose, but it needs Review because it involves API credentials, wallet private keys, uploads, proposals, and USDC settlement without enough explicit user-control safeguards.

Install only if you are comfortable letting an agent interact with an external task marketplace and wallet-related workflows. Keep API tokens and wallet private keys out of chat, logs, repositories, and shared files; prefer environment variables or a dedicated secret manager, and require manual confirmation before proposals, uploads, signing, or settlement actions.

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 (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to handle a market access token and a wallet private key for blockchain settlement, but it does not prominently warn that these are highly sensitive secrets whose misuse can lead to account compromise or loss of funds. In an MD+EXEC skill that may drive command execution and network interactions, normalizing credential use without explicit safety guidance increases the risk of accidental disclosure, insecure storage, or unintended signing workflows.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill provides executable examples for proposing on tasks, delivering artifacts, and checking wallet-related state, but it does not clearly warn that these operations may transmit user data, publish proposals, upload files, or trigger financial/settlement side effects. Because the skill advertises `exec` capability and interacts with a task marketplace plus USDC workflows, users could unknowingly cause external actions with reputational, privacy, or monetary consequences.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.