Security audit

Multi-Agent CN

Security checks for vulnerabilities and agentic risk

Overview

This skill openly provides a Chinese multi-agent dispatcher, but it forces work through persistent sub-agents and restricts the main agent’s normal tools, so users should review it before installing.

Install only if you intentionally want a Chinese-language dispatcher that delegates work to five reusable sub-agent sessions. Avoid using it for sensitive, private, credential-bearing, or regulated tasks unless you are comfortable with that context being copied into persistent delegated sessions.

A.I.G

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

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:44
Finding: Host-Agent Role and Tool-Control Hijacking
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (3)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description labels this as a Chinese version and the instructions are entirely framed for Chinese-language operation, but the file does not offer the user a language choice or explain a necessary locale restriction. This creates a natural-language policy issue because the skill appears to force a specific language by default.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description advertises the skill as a generic multi-agent dispatcher with 'no topic binding' and broad task delegation, but it does not define any scope limits, safety boundaries, or exclusions. In practice, this can cause the skill to activate for a wide range of user requests and route sensitive or high-risk tasks to sub-agents without clear guardrails, increasing the chance of misuse or unsafe delegation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description presents the skill as a Chinese-version system and emphasizes Chinese-language behavior, but it does not clearly state that language selection is optional or user-controlled. This can override user expectations, reduce transparency, and in some cases cause misunderstandings of instructions or safety warnings if the user did not opt into Chinese output.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.