Skill Security Audit

• Outcome: Pass
• Latest audit: Sep 12, 2026 · 5:40 AM UTC
• Version: 1.0.0

Overview

This skill is a simple review checklist for auditing other skills and does not include code, network calls, persistence, or hidden data access.

Installers should understand that the skill is primarily written in Chinese and intended for auditing skill text supplied by the user. Use it with explicit file inputs and review its findings as advisory rather than automatic security decisions.

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 (3)

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: This markdown file contains user-facing natural-language guidance entirely in Chinese, which effectively forces a specific language for use of the skill. The policy allows locale constraints only when the skill offers user choice or clearly documents a justified region/language limitation, which is not present here.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The manifest description says the skill audits installed skills for several broad categories, including "overscoped triggers," but provides no specific invocation phrases, scope boundaries, or exclusion conditions. In a manifest file, this lack of specificity can make it unclear when the skill should activate versus when general discussion of security or audits should not trigger it.

Natural-Language Policy Violations

Low

• Confidence: 90% confidence
• Finding: The manifest description is written entirely in Chinese, which can imply a language-specific experience without any stated opt-in, alternative locale support, or region-specific justification. This may conflict with language/locale policy expectations when the skill is otherwise not documented as China-specific.

Static analysis

No suspicious patterns detected.