Back to skill

Security audit

产品经理求职助手

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent interview-coaching skill, but users should share only redacted resume or experience details.

Safe to install for PM interview preparation. Before using it, remove or mask phone numbers, email addresses, home addresses, government ID numbers, exact compensation, and any unrelated private information from your resume or examples.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill hard-codes Chinese as the interaction language without asking for user preference or offering an alternative. This can exclude or confuse users and may cause them to disclose sensitive information without fully understanding the prompt, but it is not directly a code-execution or account-compromise issue.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill asks the user to provide a resume, which commonly contains sensitive personal data such as phone number, email, work history, education, and sometimes government identifiers, but gives no privacy warning or minimization guidance. In a job-coaching context this increases the likelihood of unnecessary exposure of personal data to the system or downstream tools.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The initialization message proactively invites users to send their resume immediately, again without any notice about sensitive personal information or data minimization. Because this is the first interaction, users are especially likely to overshare complete documents before understanding privacy risks, making the prompt more dangerous in context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.