Back to skill

Security audit

Work Buddy 中文版

Security checks for vulnerabilities and agentic risk

Overview

This Chinese work-buddy skill only changes conversational style for light proactive workplace check-ins and does not add code, persistence, credentials, or privileged access.

Install this if you want the assistant to speak in Chinese and behave more like a restrained work companion with occasional concise check-ins. Avoid it if you prefer a strictly reactive assistant or do not want proactive workplace-style follow-up messages.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill name and title label it as a Chinese-only variant, and the description specifies '中文陪伴规则' with no indication that the user can opt into another language. This creates a language/locale policy concern because the skill appears to force a specific language rather than offering a choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description defines very broad activation scenarios such as general work companionship, light check-ins, and naturally reappearing after silence. This can cause the skill to trigger across many ordinary conversations, unexpectedly altering assistant behavior and increasing the chance of intrusive or context-inappropriate proactive messaging.

Content

No source excerpt is available for this finding.