Back to skill

Security audit

moumou-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only business strategy advice skill with no code execution, data access, persistence, or hidden behavior.

Install this if you want a Chinese-language executive strategy advisor style. Be aware it may trigger for a wide range of business-direction questions and may answer in its prescribed Chinese persona unless the platform or user instructions override that style.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger criteria are extremely broad: the skill must activate not only on explicit strategy terms but on any query involving 'major business direction choices.' In a multi-skill or general assistant environment, this can cause over-triggering, hijacking unrelated conversations and steering responses into a prescriptive executive-advisor mode without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill content is entirely in Chinese and includes a fixed Chinese greeting and persona style, which can force a specific language and presentation regardless of the user's preferences. This is risky because it can degrade usability, confuse users, and override system/user language expectations, especially when the skill auto-activates broadly.

Content

No source excerpt is available for this finding.