Security audit

AI KEY·从哪儿下手

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent goal-decomposition coaching skill, with some persistence and routing/UX caveats but no evidence of hidden execution, exfiltration, or destructive behavior.

Install this if you want a Chinese-language AI KEY workflow for breaking vague goals into measurable next actions. Be aware that it can store goal context, assumptions, checkpoints, and lessons in the configured AI KEY memory/tracking paths, so avoid using it for goals or business details you do not want persisted.

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

Medium

Confidence: 97% confidence
Finding: The skill advertises very broad trigger phrases like general problem-solving and goal-setting requests, which can cause it to activate outside its intended scope. This creates routing and consent risk: users asking ordinary questions may be funneled into a rigid workflow that asks for unnecessary personal/business context and may override more appropriate specialized skills.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill enforces a mandatory communication style ('零术语') without offering user choice, which is a genuine UX and safety concern because it can suppress precision or prevent adaptation to the user's preference and expertise level. In edge cases, forced simplification may omit important nuance, especially for analytical, business, or risk-sensitive topics.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The entire skill file is written as Chinese-only operational guidance, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or region-specific context. Under the policy rule, a fixed language/locale without opt-in or justification is a natural-language policy concern.

Static analysis

No suspicious patterns detected.