security-review
仓库创建 2024年12月9日最近提交 4 小时前SkillHot 收录 3 小时前
▸ 精选理由
提供仓库特定的安全风险点与必须的核查步骤,便于合规审查。
▸ 风险提示
审查建议可能涉及权限与配置变更,执行时需谨慎
这个 Skill 做什么
针对 ChatbotX 的安全检查清单,覆盖租户隔离与未受信内容处理等。
在对 ChatbotX 做权限、工作区范围、通道 webhook、AI 工具或处理不受信内容的改动前,先按仓库级清单自检租户隔离、prompt 注入风险、Bash 允许列表和密钥处理等要点。适合提交安全敏感改动前把关,复杂问题再交给全局 security-reviewer 深度分析。
▸ 展开 SKILL.md 英文原文
Use before committing changes to auth, workspace scoping, channel webhooks, AI tools/MCP, permission settings, or anything handling untrusted channel content in ChatbotX. A repo-specific security checklist covering tenant isolation, prompt injection via channel content, the Bash permission allowlist, and secret handling. Read before security-sensitive work; pair with the global security-reviewer agent for deep dives.
524
Stars
116
Forks
21
仓库内 Skill
积累中
7 日增星
安装 / 使用
给你的 Agent 一句话(通用)
帮我安装这个 skill:https://raw.githubusercontent.com/ChatbotXIO/ChatbotX/main/.agents/skills/security-review/SKILL.md或 curl 直取 SKILL.md
curl -fsSL "https://raw.githubusercontent.com/ChatbotXIO/ChatbotX/main/.agents/skills/security-review/SKILL.md"SKILL.MD 节选查看完整文件 ↗
# Security Review (ChatbotX) A focused, repo-specific checklist. For OWASP-depth analysis dispatch the global `security-reviewer` agent; this skill is the ChatbotX-specific surface map and the things that bite here. ## 1. Tenant isolation (the #1 risk in a multi-workspace product) - Every query that returns workspace data MUST be scoped by `workspaceId`, OR by an id that is provably workspace-bound by construction (trace it). - Builder APIs go through `workspaceAuthorizedMidddleware` / `workspaceTokenAuthMidddleware` (triple-d — preserved typo). Confirm new oRPC routes use the authorized stack, not an unauthenticated handler. - RAG/embedding queries: see the `rag-eval` agent. A `sourceId`
via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有