Clawhub Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is review-worthy because it can run autonomously with bounty-account API keys and an optional wallet key, submitting proposals/work and staking funds with unclear approval boundaries.

Review carefully before installing. Use restricted API keys, start in proposal-only or dry-run mode, disable staking unless needed, use only a dedicated low-balance hot wallet, and require manual approval for every claim, stake, proposal, and work submission.

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: 92% confidence
Finding: The skill’s quick-start path encourages users to enable autonomous operation immediately, while the risks of continuous polling, automatic proposal submission, and possible financial or reputational consequences are only described later and less prominently. In an agent skill that can act on external platforms and potentially use wallet credentials, weak upfront disclosure increases the chance that users will activate behavior they do not fully understand or constrain.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal