Back to skill

Security audit

求职面试全能助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language job interview and resume coaching skill with no executable code, persistence, or hidden data transfer, though users should avoid sharing unnecessary personal details.

Install only if you want Chinese-language job search coaching. When using resume or interview templates, share only the personal information needed for the task, redact contact details during drafting when possible, and treat the listed custom service email as an optional external contact outside the skill.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The invocation description is broad enough to match ordinary career-related conversation, which can cause the skill to activate in situations where the user did not clearly intend to use a specialized job-search workflow. Over-broad triggering increases the chance of unnecessary collection or processing of personal career information and can interfere with normal assistant behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The resume template explicitly requests personal information such as name, phone number, email, and profile links, but provides no privacy notice, minimization guidance, or warning against sharing unnecessary sensitive data. In a job-assistance context, users are likely to paste real PII, making inadvertent exposure or oversharing more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The phrase telling users to say they need custom service is vague and can redirect users into an off-platform service flow without clear boundaries, consent language, or safety checks. This creates a pathway for social engineering, privacy leakage, or unreviewed commercial engagement outside the normal skill scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill manifest and instructional content are fully in Chinese, with no indication that the user can choose another language. This can violate language/locale policy when a skill effectively forces a language without explicit user opt-in or justification for a region-specific scope.

Content

No source excerpt is available for this finding.