Security audit

Karpathy Guidelines

Security checks for vulnerabilities and agentic risk

Overview

This is a simple coding-guidance skill with no bundled code or sensitive access, though its activation language is broad.

Install this if you want an agent to follow conservative coding habits. Be aware it may activate on many coding tasks, and review whether you want it creating or updating a lessons file after work is completed.

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 (2)

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: 描述文本整体以中文规定技能用途，但未说明这是可选语言偏好，也未向用户提供语言切换或明确的用户选择机制。按照语言/locale 政策要求，若技能隐含强制特定语言而无用户 opt-in，可能构成自然语言策略违规。

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The auto-activation triggers are broad enough to overlap with many ordinary coding requests, which can cause this skill to be invoked unexpectedly and steer agent behavior without explicit user intent. In multi-skill environments, this increases prompt-scope confusion and can indirectly influence code review or implementation workflows beyond what the user asked for.

Static analysis

No suspicious patterns detected.