ClawHub
Back to skill

Security audit

Zengming

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language reference skill for querying public ideas and quotes attributed to Professor Zeng Ming, with no code execution, persistence, credential use, or hidden data access.

This skill appears safe to install as a static reference aid. Users should treat its built-in knowledge as a brief public-material summary rather than an authoritative or current source, especially for latest statements or exact quotations.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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
88% confidence
Finding
The invocation examples are overly broad because they match generic queries about '曾鸣' without clearly constraining the subject matter to the professor’s published ideas, speeches, or business viewpoints. This can cause unintended skill activation for ambiguous name-based queries, leading to user confusion, irrelevant responses, or accidental routing to this skill when the user meant a different person or a broader topic.

Static analysis

No suspicious patterns detected.