跳到主内容
智客 ZICQ

技能库 智客分类:安全测试 secure-ai-agent-coding

Secure Ai Agent Coding

构建,审查,或硬化AI代理,LLM应用,RAG,工具调用,编码代理,以及具有安全逐一默认控制的代理工作流程. 触发于即时注射,工具权限,批准,AI数据处理,RAG中毒,可观察性,或安全CI. 不要用于非AI应用程序.

72 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

构建,审查,或硬化AI代理,LLM应用,RAG,工具调用,编码代理,以及具有安全逐一默认控制的代理工作流程. 触发于即时注射,工具权限,批准,AI数据处理,RAG中毒,可观察性,或安全CI. 不要用于非AI应用程序.

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:secure-ai-agent-coding、Decision Tree、Quick Reference、Core Workflow、Control Router、Operational Scripts。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/implementation-patterns.md、references/controls.md、scripts/scan_patterns.py、references/review-workflow.md、references/governance.md、references/threat-model.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.

secure-ai-agent-codingDecision TreeQuick ReferenceCore WorkflowControl RouterOperational ScriptsSource ScopeGotchas

兼容:Requires: python3 for optional local pattern scanning. No external packages required.

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
secure-ai-agent-coding
description
Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec.
compatibility
Requires: python3 for optional local pattern scanning. No external packages required.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 7
  • references/implementation-patterns.md
  • references/controls.md
  • scripts/scan_patterns.py
  • references/review-workflow.md
  • references/governance.md
  • references/threat-model.md
  • references/gotchas.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「secure-ai-agent-coding」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-9139e96f125bf85e-%E5%AE%89%E5%85%A8-Ai-%E4%BB%A3%E7%90%86%E7%BC%96%E7%A0%81.html
请存为 .cursor/skills/secure-ai-agent-coding/SKILL.md 或 .claude/skills/secure-ai-agent-coding/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/jpcaparas/skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/jpcaparas/skills' --list

npx skills add 'https://github.com/jpcaparas/skills' --skill 'secure-ai-agent-coding'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: secure-ai-agent-coding description: "Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls. Trigger on prompt injection, tool permissions, approvals, AI data handling, RAG poisoning, observability, or safety CI. Do NOT use for non-AI appsec." compatibility: "Requires: python3 for optional local pattern scanning. No external packages required." metadata: version: "1.0.0" short-description: "Secure AI agent coding review and hardening" openclaw: category: "development" requires: bins: [python3] references:

  • review-workflow
  • controls
  • implementation-patterns
  • threat-model
  • governance
  • gotchas

secure-ai-agent-coding

Build or review AI agents and LLM applications so their blast radius stays small, their behavior is auditable, and high-impact actions require explicit control.

Decision Tree

What is the user asking for?

  • Build a new AI agent or LLM feature: Read references/implementation-patterns.md, then apply references/controls.md before writing integration code.
  • Review an existing codebase or design: Run scripts/scan_patterns.py /path/to/project --json if source code is available, then read references/review-workflow.md.
  • Add tools, system calls, code execution, database writes, API calls, or email/message sending: Treat it as a high-risk action surface. Read references/implementation-patterns.md and require allowlisted tools, per-action authorization, rate limits, rollback, and approval gates.
  • Handle user data, production data, documents, web pages, email, vector stores, embeddings, or fine-tuning data: Read references/governance.md and references/threat-model.md before designing prompts or retrieval flows.
  • Debug a safety incident, unexpected model behavior, prompt injection, data leak, or harmful automation: Read references/review-workflow.md and references/gotchas.md, preserve logs, stop autonomous actions, and recover from a known safe state.
  • The request is only generic web app security with no AI, model, RAG, tool-call, or agentic workflow: Do not use this skill unless the AI-specific attack surface is part of the task.

Quick Reference

| Task | Action | |------|--------| | Find likely dangerous patterns | Run python3 scripts/scan_patterns.py /path/to/project | | Classify risk | Tier each agent action by impact, reversibility, data sensitivity, and external side effects | | Protect prompts | Separate instructions from untrusted data; validate, delimit, and minimize context | | Protect tool calls | Use explicit allowlists, scoped credentials, per-action authorization, and rate limits | | Protect users and data | Classify data, minimize disclosure, redact logs, verify consent, and avoid raw production data in test systems | | Protect downstream systems | Validate structured model output before using it in code, SQL, shell, APIs, or UI rendering | | Protect production | Add monitoring, anomaly alerts, safety regression tests, rollback plans, and incident response steps | | Review exceptions | Document why a control does not apply, who accepted the risk, and when it expires |

Core Workflow

  1. Map the AI surface: model calls, prompts, retrieved content, tools, state, credentials, data stores, and external side effects.
  2. Classify every input as untrusted unless it is generated by a trusted server-side component and still validate it.
  3. Classify every action the agent can take. Default to reversible, low-privilege actions and escalate high-impact actions to human approval.
  4. Design controls before implementation: schemas, allowlists, server-side authorization, idempotency, rate limits, locks, rollback, and audit logs.
  5. Keep sensitive data out of prompts and logs unless the model truly needs it. Prefer redaction, tokenization, anonymization, or synthetic data.
  6. Validate AI output before it reaches downstream interpreters, renderers, databases, APIs, file systems, or shell commands.
  7. Test safety controls in CI and again after model, prompt, framework, dependency, retrieval, or tool changes.

Control Router

| Area | Load | |------|------| | End-to-end review process, severity, report format | references/review-workflow.md | | Control catalog and evidence checklist | references/controls.md | | Copyable implementation patterns | references/implementation-patterns.md | | AI-specific threat scenarios and risk tiers | references/threat-model.md | | Inventory, consent, model updates, lifecycle, and operations | references/governance.md | | Common failure modes and reviewer traps | references/gotchas.md | | Source conversion notes and scope exclusions | references/source-policy.md |

Operational Scripts

Use scripts/scan_patterns.py as a first-pass heuristic scanner, not as proof of safety.

python3 scripts/scan_patterns.py /path/to/project
python3 scripts/scan_patterns.py /path/to/project --json --fail-on high

The scanner intentionally favors review prompts over automated verdicts. Treat findings as places to inspect.

Source Scope

This skill adapts the engineering-applicable controls from Galdren's "Secure AI & Agent Coding Policy" into an agent skill. It keeps the parts that can drive code review, architecture decisions, local checks, and production hardening. It leaves legal judgment, organization-specific approvals, and physical security as prompts to involve the right team rather than pretending a coding skill can resolve them.

Gotchas

  1. Prompt-only defenses are not enough. Enforce authorization, validation, and tool limits outside the model.
  2. A model used as a validator is still an AI input surface. Validate its inputs and outputs like any other component.
  3. "Authenticated user" is not the same as "authorized agent action." Check each action separately.
  4. Logs can become a data leak. Record enough to investigate, but redact secrets, personal data, and sensitive context.
  5. Model or framework upgrades can change behavior without a code diff. Retest safety and output contracts after every change.
  6. Broad tool access turns small prompt failures into production incidents. Keep the agent footprint minimal at every step.

相关技能

安全测试

Skill Vetter

人工智能特工的安全第一技能审查。 在安装来自 ClawdHub, GitHub 或其他来源的任何技能之前使用 。 检查红旗,许可范围,可疑图案.

安全测试

Moltguard

MoltGuard——由OpenGuardrails担任OpenClaw保安. 安装 MoltGuard 以保护你和你的人类免受迅速注射、数据过滤和恶意命令的影响。 资料来源:https://github.com/openguardrails/openguardrails/tre…

安全测试

Security Auditor

用于审查安全漏洞代码,实施认证流,审计OWASP Top 10,配置CORS/CSP头,处理秘密,输入验证,SQL注射预防,XSS保护,或任何与安全相关的代码审查.

安全测试

Skill Vetter

安装任何AI代理技能前的安全审查协议. 红旗侦取入证盗取,疏通密码,放出. 风险分类:低/中/高/高。 编制结构化审查报告。 不先运行此功能, 绝不安装不信任的技能 .