Security audit

Jue AI Awakening Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language self-review workflow skill with broad activation wording, but it contains only disclosed Markdown guidance and no hidden code, persistence, credential handling, or exfiltration behavior.

Install this if you want a Chinese-language process that makes the agent more persistent and evidence-driven after failures. Be aware it may activate on common phrases like asking it to rethink, try another way, check best practices, or review code, and it may spend more effort using tools before asking you for clarification.

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 (6)

Vague Triggers

High

Confidence: 96% confidence
Finding: The skill declares broad trigger conditions such as user dissatisfaction, repeated attempts, and generic phrases like '再想想' or '换个方法', which are common in ordinary interaction and not tightly scoped to a specific task class. This can cause unintended activation and instruction override behavior, making the agent switch into this skill in many benign contexts and alter normal user-directed flow.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The entire skill is authored in Chinese and presents all trigger phrases, instructions, and output formats only in Chinese, with no indication that language selection is optional. For a general-purpose skill, this effectively imposes a language policy without user opt-in or documented regional justification.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The preemptive trigger section maps broad user prompts like requests for clarity, best practices, or code review directly into automatic skill activation without clear scope boundaries. Because these prompts are routine across many tasks, the skill may activate unexpectedly and reshape agent behavior even when the user did not intend to invoke this framework.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This reference file presents all instructions, headings, and examples exclusively in Chinese, which can amount to a language policy violation if the organization expects skills to avoid forcing a specific language without user opt-in. There is no indication that users may choose another language or that the file is intentionally limited to a Chinese-speaking or region-specific context.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file presents all instructions and operational guidance exclusively in Chinese, and it does not offer the user any language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file is entirely written in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for natural-language constraints, forcing a specific language without user opt-in is a locale/language policy violation.

Static analysis

No suspicious patterns detected.