ClawHub
Back to skill

Security audit

ClawHub Publish Conventions

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only publishing guide with visible examples and no executable payload or hidden behavior.

Safe to install as documentation. Review any Docker and clawhub publish commands before running them, and avoid placing secrets in SKILL.md, README files, command examples, or subprocess environments.

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.