ClawHub
Back to skill

Security audit

OUA 统一智能评估

Security checks for vulnerabilities and agentic risk

Overview

This is a purpose-aligned AI evaluation skill with an optional local scoring/report script; the main issue is broad trigger wording that could activate it unintentionally.

Before installing, consider narrowing the trigger phrases if you use many benchmarking or evaluation skills. Run the scoring script only on intended assessment JSON, and note that HTML reports may contact a CDN to render charts.

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
91% confidence
Finding
The trigger phrase list includes generic terms such as 'AI全能评估', 'benchmark', and 'evaluation' that can overlap with ordinary user requests about AI testing or benchmarking. Overly broad triggers can cause unintended activation of the skill, leading to prompt hijacking of normal conversations, user confusion, or invocation in contexts where the skill was not intended to run.

Static analysis

No suspicious patterns detected.