ClawHub
Back to skill

Security audit

注册审核员考试技能（主观题）

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only exam study skill that reads local exam reference files and does not request code execution, network access, credentials, or persistence.

Install this if you want a Chinese registered-auditor exam practice helper that works from local reference materials. Be aware that its trigger wording could be tightened, so use it for the named auditor-exam subjects rather than general study tasks.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is broad enough to trigger on generic exam-prep, study, question-answering, and planning requests, which can cause the agent to activate this skill outside its narrowly intended auditor-exam context. Over-broad activation increases the chance of instruction hijacking or unintended file access within the skill’s scope, especially since the skill is designed to read local reference content based on user-supplied subject/date parameters.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.