Security audit

Task Router

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language task router with broad automatic routing, but it contains no hidden code, persistence, credential handling, or destructive behavior.

Before installing, review the named target agents and skills because this router may automatically hand broad categories of tasks to them, including trading-related or document/calendar workflows. Use extra confirmation for sensitive actions.

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

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 (3)

Vague Triggers

High

Confidence: 95% confidence
Finding: The skill declares automatic triggering for essentially any incoming user task without meaningful scope boundaries or consent. In a routing skill, this can cause unintended interception of unrelated requests, misrouting to other agents/skills, and expansion of the skill’s influence beyond least-privilege expectations.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The natural-language description and operating instructions are entirely in Chinese and present the skill as operating in that locale by default, with no option for user language preference. This can violate language or locale policy where skills should not force a specific language without explicit opt-in or documented justification.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The routing table uses broad, ambiguous keywords such as '项目', '代码', '研究', and '分析' that can match many unrelated requests. This increases the chance of false routing, causing sensitive or safety-relevant tasks to be sent to the wrong agent and potentially exposing user data or producing inappropriate actions.

Static analysis

No suspicious patterns detected.