Clawdhub Copy

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed ClawdHub CLI wrapper, but it gives an agent broad ability to install, force-update, bulk-update, and publish skills with limited guardrail guidance.

Install only if you want the agent to manage ClawdHub skills. Require explicit approval before any install, update, `update --all`, `--force`, `--no-input`, login, or publish command; review target directories and prefer pinned versions from trusted publishers.

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: 93% confidence
Finding: The skill explicitly documents `clawdhub login`, `whoami`, and `publish` actions that interact with an external service, but it provides no warning that authentication links the user's account and that publishing can transmit local skill contents and related metadata off-host. In an agent-skill context, this omission is risky because users may invoke these commands without realizing they are performing networked, potentially irreversible actions involving credentials and local files.

VirusTotal

57/57 vendors flagged this skill as clean.

View on VirusTotal