Security audit

coding-as-dressing

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language teaching skill for explaining code with clothing analogies, with no code execution, persistence, credential use, or data access behavior.

Install this if you want Chinese code explanations using clothing analogies. Be aware it may trigger on generic Chinese requests like asking what code means, so users who want normal explanations may prefer narrower activation wording.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The skill content and behavior are defined only in Chinese and do not offer language fallback or user-choice handling, which can force responses into Chinese regardless of the user's language. This is primarily a safety/quality issue because it can override user intent or create confusion, but it does not by itself enable code execution, data exfiltration, or privilege escalation.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger conditions are broad enough to capture generic requests like '这段代码什么意思' or '帮我用简单的话解释', which overlap with ordinary code-explanation tasks rather than the niche 'dressing metaphor' mode. This can cause unintended activation, leading the agent to respond in an unnecessary constrained style and reducing reliability or appropriateness of answers.

Static analysis

No suspicious patterns detected.