ClawHub
Back to skill

Security audit

quality-assurance

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only QA skill for reviewing other OpenClaw skills, with some overbroad certification language but no hidden execution, persistence, credential handling, or destructive behavior.

Install this as an advisory quality-review helper, not as a final security or release authority. Its reports can help structure testing, but users should still apply normal security review, domain-specific validation, and human release judgment before shipping a skill.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill description and body position this as a universal gatekeeper for validating 'any skill' and to be used broadly before shipping, but they do not define clear scope boundaries or safe invocation constraints. In practice, this can cause the skill to activate on generic validation or testing requests, leading to over-broad routing, accidental use in inappropriate contexts, and excessive trust in an internal QA/certification result as an authoritative approval signal.

Static analysis

No suspicious patterns detected.