Ai Automation Consulting

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 1:34 AM UTC
• Version: 2.0.0

Overview

This is a Chinese-language AI automation consulting advertisement with contact links, not an executable or privileged skill.

Install this only if you want a Chinese-language consulting-oriented skill that may surface sales packages and contact details. Treat it as advisory marketing content, and do not let it connect tools or automate workflows unless you separately review and approve any concrete implementation steps.

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
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The skill description is written so broadly ('AI automation consulting' for saving time and money) that it can match a wide range of ordinary productivity requests without clear boundaries. This increases the chance of over-activation or inappropriate routing, which can expose users to unsolicited marketing or cause the skill to engage outside its intended scope.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The marketing questions describe very common tasks like replying to messages, organizing reports, and writing emails, which overlap with a large portion of normal assistant interactions. Without explicit trigger criteria, this broad problem framing can cause the skill to activate on generic requests that were not intended to invoke a commercial consulting skill.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The workflow automation section claims it can connect tools, trigger tasks, and reduce human intervention, but it does not define scope, approval requirements, or safety limits. In an agent ecosystem, ambiguous automation claims can encourage use in sensitive operational contexts without adequate safeguards, increasing the risk of unintended actions or misuse.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The manifest description is written entirely in Chinese, and the tags also indicate a Chinese-language orientation, but the file does not state that the skill is Chinese-only, optional by locale, or intended for a specific region. This can constitute a language/locale policy issue when users are not explicitly offered a language choice or informed of the constraint.

Vague Triggers

Low

• Confidence: 82% confidence
• Finding: This manifest description says the skill is suitable for 'SMEs, freelancers, and people who want efficiency,' which is very broad and does not indicate when the skill should or should not be invoked. For manifest files, vague, expansive descriptions can contribute to unintended activation if they are used as invocation or routing cues.

Static analysis

No suspicious patterns detected.