ClawHub
Back to skill

Security audit

Interview Review

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown interview-review skill that asks users for interview text and gives coaching advice, with no code execution or hidden data access.

Install this if you want Chinese-language coaching on completed interviews. Be mindful that interview transcripts may contain personal or employer-sensitive information, so only provide details you are comfortable sharing with the assistant.

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 (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation description is broad enough to trigger on loosely related "post-interview analysis" requests, which can cause the assistant to invoke this skill when the user did not clearly ask for a structured interview review. That increases the chance of scope hijacking, unnecessary collection of sensitive interview content, and reduced user control over tool/skill routing.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill content is entirely written to operate in Chinese and implicitly steers output style and interaction language without checking the user's preferred locale. This can cause unintended language coercion, degrade usability for non-Chinese users, and create misrouting or misunderstanding when the surrounding system expects language-neutral behavior.

Static analysis

No suspicious patterns detected.