Security audit

Meta Control - Agent Orchestration

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed sub-agent orchestrator, but it gives broad background execution and monitoring authority without clear user approval or scope limits.

Install only if you want a Chinese-language orchestration skill that can delegate work to background sub-agents. Before using it on sensitive projects, require explicit confirmation for web crawling, script execution, automation, monitoring, file changes, credential use, and any long-running background task.

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly describes spawning background sub-agents, including an '执行 Agent' that can run scripts and automation, while emphasizing that the main agent will continue chatting and only report back when needed. This creates a risk of impactful actions being taken without clear user awareness, real-time confirmation boundaries, or disclosure of what sub-agents are permitted to do.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The description states that the skill acts as a master controller that dispatches sub-agents for background operations, but it does not define when this authority should be invoked or what boundaries apply. In an orchestrator skill, unclear activation and scope can cause over-broad delegation, unintended autonomous actions, or privilege expansion through downstream sub-agents.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. The skill description and instructions are entirely in Chinese, which can implicitly force a specific language experience without user opt-in or an explanation that the skill is intended only for a Chinese-language context.

Natural-Language Policy Violations

Low

Confidence: 76% confidence
Finding: The skill name and description are presented only in Chinese, with no indication that users can choose another language or that the skill is region-specific. This may violate language/locale policy if the organization requires user language choice rather than implicitly enforcing a single language.

Static analysis

No suspicious patterns detected.