Back to skill

Security audit

面试题库与评分表

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only HR interview-question helper with disclosed, purpose-aligned behavior and no evidence of code execution, data exfiltration, persistence, or privilege use.

Reasonable to install for HR interview-kit generation. Be aware that generic phrases like “评分表” or “把这些整理成一张表” may invoke it in recruiting conversations, so review outputs for legal and privacy compliance and avoid asking about protected or sensitive personal attributes.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keywords are broad generic recruiting terms such as '面试题' and '评分表', which can match ordinary HR conversation and cause the skill to activate unintentionally. This is not code-execution dangerous, but it can hijack unrelated prompts, create confusing routing, and increase the chance that the skill processes context it was not specifically invoked for.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language examples are open-ended and conversational, especially phrases like '按上面的结果改成更简短的版本' and '把这些整理成一张表', which are common follow-up requests in many contexts. That makes it hard to distinguish a deliberate skill invocation from ordinary chat editing, increasing accidental activation and context bleed across unrelated tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.