ClawHub
Back to skill

Security audit

CIE 剑桥考试监考技能手册

Security checks for vulnerabilities and agentic risk

Overview

This is a static Cambridge exam invigilation reference skill with minor activation and language caveats, but no hidden code, persistence, credential use, or privileged behavior.

Before installing, treat this as a Cambridge-specific invigilation checklist and confirm key times, scripts, and AI/malpractice procedures against the current official Cambridge documents for your exam series. Be aware it may activate on broad exam-management wording, so check that it is relevant to your board and context.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list includes broad, generic terms such as 'exam day' and '考试管理', which can cause the skill to activate in contexts far beyond Cambridge invigilation. Unintended invocation can route unrelated user requests into this skill, producing incorrect operational guidance in sensitive education or compliance workflows.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The text states the instructions must be read in English and '不得改用中文,' which imposes a fixed language requirement. While this may reflect external exam rules, the file does not clearly frame the constraint as a justified policy exception or offer any user language choice for the rest of the skill content.

Static analysis

No suspicious patterns detected.