Back to skill

Security audit

筛选沟通简历

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow recruiting helper that reviews visible BOSS Zhipin candidates and reports matching profiles to the user, with privacy precautions needed but no deceptive or unsafe behavior found.

Before installing, confirm you are authorized to access and process the candidates' information, verify the DingTalk destination, and share only the fields needed for recruiting decisions under your organization's privacy rules.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs collecting and transmitting identifiable candidate data (name, education, work history, salary expectations, technical stack) to a DingTalk account without any privacy notice, minimization rule, consent check, or secure-handling guidance. Because the data comes from a recruiting platform and includes personal information, forwarding it through messaging creates a real privacy and data-governance risk, especially if the recipient, retention, or authorization is not validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

All user-facing instructions are fixed in Chinese, and the skill does not indicate that another language can be used on request. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.