Back to skill

Security audit

观势专家 — org-expert

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language organizational diagnosis guide with no executable code or hidden high-impact behavior.

Before installing, consider whether your users need Chinese-language organizational diagnosis support. The skill may handle sensitive talent and management assessments, so users should avoid providing unnecessary personal or confidential employee details and keep outputs appropriately restricted.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and the entire skill guidance are written to operate in Chinese, including trigger/context language such as "Use when 被观势 Chief 调度执行..." and all user-facing methodology/output instructions. There is no indication that users may choose another language or that the Chinese-only constraint is a documented, justified regional requirement.

Content

No source excerpt is available for this finding.