求职全链路（规划·岗位·简历·面试·投递·HR）

• Outcome: Pass
• Latest audit: Sep 24, 2026 · 3:54 AM UTC
• Version: 1.6.1

Overview

This is a text-only career-coaching skill with disclosed resume/JD/salary handling and no code, storage, credential use, or hidden data transfer.

Install if you want a Chinese-language career-planning assistant. Avoid sharing unnecessary sensitive details such as ID numbers, bank information, full addresses, or exact salary documents; use ranges where possible and verify live salary, legal, offer, and market claims independently.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (17)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The description and trigger conditions are broad enough to match nearly any job-seeking or career-related request, which can cause the skill to activate when the user did not clearly intend to invoke this specialized workflow. Over-broad routing increases the risk of context hijacking, unnecessary collection of personal career data, and interference with more appropriate skills or default assistant behavior.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The quick-start guidance says users can trigger the skill with copied opening scripts and even 'zero input,' which encourages activation from vague prompts without confirming scope or consent. That makes unintended invocation more likely and may cause the system to apply default assumptions and workflow steps to underspecified user requests.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: Stating that the main users are '中国境内求职者（全中文交互...)' and framing the workflow around Chinese-only interaction without explicit user preference can improperly constrain language behavior and reduce accessibility for multilingual or non-Chinese users. In a shared assistant environment, this can lead to incorrect routing, poor user experience, or exclusion when the user's requested language differs from the skill default.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The example phrases are very generic and encourage invocation from minimal user input like 'help me do career planning' or 'help me edit my resume,' which are common utterances that may appear in broader conversations. Because the skill supports chained execution across planning, resume, and delivery workflows, accidental triggering could cause unintended processing of sensitive employment data or undesired task switching.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger guidance uses broad natural-language phrases for career-help intents, which can overlap with ordinary conversation and cause the skill to activate when the user did not explicitly intend to invoke it. In an agent environment, unintended activation can lead to unnecessary routing, context capture, or execution of downstream modules, especially because this skill can chain into multiple submodules and external companion skills.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The file’s natural-language instructions and examples are entirely in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: The entire framework, including user-facing questions and required output phrasing, is written as mandatory Chinese-language guidance with no opt-in, alternative language path, or statement that the skill is intentionally limited to a Chinese-speaking context. This creates a natural-language locale policy concern because it implicitly enforces one language for all users.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: This markdown skill prescribes all instructions, outputs, and trigger phrases in Chinese only. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Natural-Language Policy Violations

Medium

• Confidence: 89% confidence
• Finding: A hard requirement to operate in Chinese without user language choice can cause misunderstanding, reduce informed consent, and degrade the accuracy of advice if the user is more comfortable in another language. In a skill that handles nuanced employment decisions and collects user background, language mismatch increases the risk of incorrect interpretation of constraints, goals, or legal/compensation details.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger criteria are broad enough to match ambiguous everyday career-related statements, which can cause the agent to route into this skill when the user did not intend a structured career-planning workflow. In practice this can override user intent, lead to unnecessary collection of personal employment data, and produce over-scoped guidance in the wrong context.

Natural-Language Policy Violations

Medium

• Confidence: 96% confidence
• Finding: This markdown file presents all instructions, triggers, and output formats only in Chinese. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale limitation is explicitly justified, which is not present here.

Natural-Language Policy Violations

Medium

• Confidence: 82% confidence
• Finding: The module is written to operate in Chinese without offering a language negotiation path, which can cause the agent to respond in an unintended language or mishandle user instructions. While not a classic security flaw, it can undermine reliable execution and user understanding, especially if the system processes sensitive career information and the user cannot accurately validate the output.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are broad enough that ordinary interview-related conversation could unintentionally activate this skill and route the user into a rigid workflow. In a multi-skill agent, this can cause misrouting, irrelevant data collection, and reduced user control over how their request is handled.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: This markdown skill specifies all operational instructions and required output phrasing in Chinese, including fixed output templates and invocation text. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not stated here.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The invocation section says the module applies whenever a user provides a resume or describes experience and asks to organize, improve, or make it more persuasive, with trigger phrases like “帮我改简历”. These are broad everyday requests, and the file does not provide negative examples or sharper boundaries for when this module should not be invoked versus other resume-related skills.

Natural-Language Policy Violations

Low

• Confidence: 81% confidence
• Finding: All user-facing instructions and example prompts are presented only in Chinese, which can amount to an implicit language constraint. There is no statement that other languages are supported or that Chinese is optional or region-specific.

Natural-Language Policy Violations

Low

• Confidence: 94% confidence
• Finding: The file's natural-language instructions and examples are entirely in Chinese, and there is no indication that users can opt into another language or that the skill is restricted to a Chinese-speaking context. Under the policy rule, forcing a specific language without user choice can be a locale/language policy violation.

Static analysis

No suspicious patterns detected.