Back to skill

Security audit

tuotuo-10agents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese writing and productivity assistant with broad activation wording but no code, privileged access, persistence, or hidden data handling.

Install this if you want a Chinese-language assistant style for drafting and organizing business materials. Be aware it may activate for many ordinary writing or summarization requests, so users who need multilingual behavior or narrower routing may want the publisher to scope the trigger language more tightly.

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)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation text uses very broad mandatory triggers like '只要老板需要帮我写点什么/整理点什么,立即触发本skill', which can capture a large share of ordinary writing, planning, and summarization requests. This can cause unintended routing and override more appropriate skills or baseline handling, increasing the chance of prompt hijacking, mis-scoped tool use, or policy bypass through an always-on persona.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill is written entirely in Chinese and frames a fixed Chinese-speaking persona without giving the user a language choice or documenting why that restriction is necessary. In a multilingual agent environment, this can degrade transparency and user control, and may lead to incorrect handling of requests when the user's language, locale, or compliance context differs.

Content

No source excerpt is available for this finding.