ClawHub
Back to skill

Security audit

ai-governance-audit-chain

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only AI governance audit template skill with minor routing and language-disclosure issues, but no dangerous runtime behavior.

Installers should expect a Chinese-first governance template skill that may activate too broadly because of generic trigger keywords. Review generated compliance or audit content with qualified staff before relying on it, especially where legal or regulatory accuracy matters.

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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger keywords are extremely generic ('ai', 'governance', 'audit', 'chain') and are likely to collide with many unrelated prompts. This can cause unintended activation of the skill in contexts where its governance framing or instructions are irrelevant, increasing the chance of prompt-routing errors or accidental context injection into other tasks.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The manifest advertises a very broad trigger list, including generic governance and audit phrases that can match many unrelated user requests. This increases the chance the skill is invoked outside its intended scope, causing inappropriate routing, irrelevant compliance guidance, or accidental handling of sensitive organizational audit topics without clear user intent.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The description is written entirely in Chinese and implies Chinese-language behavior, but it does not disclose whether the skill supports other locales or how language selection is handled. This can cause users to receive outputs in an unexpected language, creating misunderstanding in legal, audit, or compliance contexts where precision matters.

Static analysis

No suspicious patterns detected.