Agent Sandbox
AI agents execute code, modify files, and run shell commands. Without guardrails, a bad prompt or hallucination can delete your database, overwrite production configs, or exfiltrate secrets. This skill builds safety layers — sandboxed execution, filesystem restrictions, network policies, audit trails, and kill switches
概览
Agent Sandbox provides a security framework for AI agents performing technical tasks such as code execution and file modification. Developed within the TerminalSkills/skills repository, this tool addresses risks associated with autonomous agent actions, including potential database deletions or unauthorized secret exfiltration. It implements multiple safety layers, including restricted filesystem access, sandboxed environments, and granular network policies. By establishing these guardrails, the skill ensures that agents operating in environments like Claude or Gemini remain within defined operational boundaries. The system also includes audit trails and emergency kill switches to maintain oversight. This approach allows developers to leverage the power of AI-driven shell commands and file management while mitigating the inherent dangers of hallucinations or unintended prompt execution.
使用场景
安装说明
# Review source first
open https://github.com/TerminalSkills/skills/blob/main/skills/agent-sandbox/SKILL.mdCopy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.
安全提示
This skill focuses on mitigating risks from AI hallucinations and malicious prompts by enforcing strict execution boundaries. It utilizes filesystem restrictions and network policies to prevent unauthorized data access or exfiltration. Users should review the audit trails provided by the TerminalSkills/skills repository implementation to ensure continuous compliance with security protocols.
相关 Skills
Yara Rule Authoring
trailofbits/skills
指导编写用于恶意软件识别的高质量 YARA-X 检测规则。适用于编写、审查或优化 YARA 规则时使用。涵盖命名规范、字符串选择、性能优化、从旧版 YARA 迁移以及降低误报。触发条件：YARA、YARA-X、malware detection、threat hunting、IOC、signature、crx module、dex module。
Cargo Fuzz
trailofbits/skills
设置并运行 cargo-fuzz，这是基于 Cargo 的 Rust 项目的标准模糊测试工具。涵盖 cargo fuzz init、nightly 工具链要求、fuzz_target! 测试桩、Arbitrary 派生的结构化输入、sanitizer 选项、cargo fuzz coverage 以及重现崩溃产物。适用于模糊测试 Rust crate、编写 fuzz_target!、测试 Rust 中的 unsafe 块或 FFI，或排查 cargo fuzz 崩溃。
Deep Agents Memory
langchain-ai/langchain-skills
INVOKE THIS SKILL 当您的 Deep Agent 需要内存、持久化或文件系统访问时。涵盖了 StateBackend（临时）、StoreBackend（持久）、FilesystemMiddleware 和用于路由的 CompositeBackend。
Security Audit
TerminalSkills/skills
通过扫描 OWASP Top 10 漏洞、检查依赖项中的已知 CVE、检测泄露的机密和 API 密钥，并生成优先修复建议，对代码库进行全面的安全审计。此技能结合了静态分析模式与依赖项审计工具。