building-agents@1.0.0
VERIFIED· install onlyPublisher claims: "【构建 AI Agent 实战指南】把 OpenAI《A Practical Guide to Building Agents》蒸馏成可执行的 Agent 设计方法论。覆盖：判断是否该建 Agent（vs 规则引擎）、Agent 三组件（Model/Tools/Instructions）、模型选型、工具设计、写 agent instructions、单/多智能体编排（Manager/Decentralized 模式）、Guardrails 与 human-in-the-loop。当用户说"帮我设计一个 agent""single agent 还是 multi-agent""怎么写 agent 指令""agent 工具怎么设计""agent 需要哪些 guardrails""该不该上 agent""agent 编排模式怎么选"时使用。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
| **Safety classifier** | 检测 jailbreak / prompt injection（试图窃取系统指令） |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.- guardrail 可实现为 **function 或 agent**（jailbreak 防护、相关性校验、关键词过滤、blocklist、安全分类）。Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.