ClawHub
Back to skill

Security audit

Publish To ClawHub

Security checks for vulnerabilities and agentic risk

Overview

This is a transparent instruction-only skill for helping publish a local skill to ClawHub and GitHub, with appropriate safety checks around credentials and public release.

Install this if you want an agent to help prepare and publish skills. Before approving any action, review the target directory, git diff, repository, account identity, version, and changelog, and prefer browser login, SSH, or a credential manager instead of pasting long-lived tokens into chat.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

Static analysis

No suspicious patterns detected.