Back to skill

Security audit

头脑超级风暴

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable brainstorming skill whose behavior is mostly purpose-aligned, with a caution that it can lead an agent to write and commit design documents.

Install only if you want a structured brainstorming workflow. Before use, make sure your agent asks before reading broad project context, writing docs/plans files, or creating git commits.

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
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

该技能在描述中使用“在任何创造性工作之前必须使用”这类强制且高度宽泛的激活条件,容易在大量本不需要该技能的任务中被自动触发。过度触发会放大其后续行为影响范围,例如引导读取项目状态、产出设计文档并推动后续流程,从而增加不必要的上下文暴露和操作风险。

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

技能指示将设计写入 docs/plans/... 并提交到 git,属于明确的持久化修改与版本控制操作,但文档中没有要求获得用户批准、说明副作用或提供跳过选项。若代理自动遵循这些指令,可能在未经授权的情况下修改工作区并创建提交,造成历史污染、泄露敏感设计信息或触发下游自动化流程。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
73% confidence
Finding

该文件整体以中文规定技能行为和交互方式,但未说明可根据用户偏好切换语言,也未提供显式的语言选择。按规则,强制单一语言且无用户选择可能构成语言/区域策略问题。

Content

No source excerpt is available for this finding.