ClawHub
Back to skill

Security audit

GitHub发布

Security checks across malware telemetry and agentic risk

Overview

This skill appears to help publish a Skill to GitHub, but its instructions may upload local content to a public repository without enough explicit safety checks.

Review this skill carefully before installing. Only use it after choosing the exact GitHub account, repository name, visibility, branch, and files to publish, and scan the directory for tokens, keys, private notes, customer data, or proprietary code before any push.

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 (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The invocation guidance is overly broad: '当需要发布Skill到GitHub时调用此技能' does not constrain when publishing is appropriate, what prerequisites must be met, or whether the user must explicitly confirm repository creation and code upload. In a skill that performs remote publication actions, vague triggers increase the chance of unintended execution, accidental disclosure of code, or pushing to the wrong repository/account.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documented flow includes creating a GitHub repository, adding a remote, and pushing code, but it does not warn users that these actions affect external systems and may expose local code, secrets, or proprietary content. Because this skill publishes to a remote service, missing warnings and consent boundaries materially increase the risk of unintended data exfiltration or irreversible publication to a public repository.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly directs the user to create a public GitHub repository and upload local files, but provides no warning about sensitive data exposure, accidental publication of private code, or the persistence of public commits. In this context, the skill is directly facilitating external publication, so the absence of safety checks or disclosure guidance materially increases the risk of leaking secrets, proprietary code, or personal data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.