ClawHub
Back to skill

Security audit

ClawHub发布助手

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate ClawHub publishing helper, but it asks the agent to use account credentials, edit local skill files, publish remotely, and optionally run a target skill's script without strong confirmation safeguards.

Install only if you intend to let an agent help publish skills to ClawHub. Before using it, explicitly confirm the skill path, account, slug, display name, version, changelog, and destination; do not paste tokens into chat or shell history; inspect any publish.sh before running it; and review diffs to package.json and SKILL.md before publishing.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger examples are broad, natural-language phrases such as '发布技能' and '帮我发布这个技能', which can cause the skill to be invoked in situations where the user did not intend an irreversible publish workflow. Because this skill performs login, version changes, and publication actions, accidental invocation increases the risk of unintended release of local content or execution of sensitive publishing steps.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs use of a token directly on the command line (`clawhub login --token "<你的token>" --no-browser`) without prominent credential-handling warnings. Command-line secrets can leak via shell history, process listings, logs, screenshots, or terminal recordings, making account compromise more likely if the token has publishing privileges.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.