Back to skill

Security audit

Interview Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a plain interview-coaching skill focused on China-market job search advice, with no code execution, persistence, or hidden data access.

Install this if you want China-market interview and job-search coaching. Treat salary ranges and legal/employment advice as general guidance, and ask the assistant to adapt language, region, or market assumptions if your job search is outside China.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The instruction describes the assistant as a 'professional Chinese job interview consultant,' which imposes a specific locale/context by default. The file does not indicate that users can opt into another language or regional hiring context, so it may violate the language/locale choice policy.

Content

No source excerpt is available for this finding.