ClawHub
Back to skill

Security audit

skill-audit

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent security-audit skill that inspects user-chosen skill folders and reports findings without hidden persistence or destructive behavior.

Install only if you want an agent to read and analyze skill folders you point it at. For best control, name the exact folder or inspected third-party skill files, and expect optional checks to run local CLI tools or network reachability checks when you ask for dependency, homepage, or discoverability verification.

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
86% confidence
Finding
The trigger guidance includes a catch-all phrase like "anything shaped like them," which can cause the skill to activate on overly broad or ambiguous user requests. In an auditing skill, this increases the chance of unintended invocation and tool use on folders or third-party content the user did not clearly ask to analyze.

Static analysis

No suspicious patterns detected.