Zero Trust Agents
Zero-trust security framework for deploying autonomous AI agents in an enterprise, distilled from Anthropic's official "Zero Trust for AI Agents" eBook: the Foundation/Enterprise/Advanced tier model, defenses against prompt injection, tool poisoning, memory poisoning and supply-chain attacks, and an 8-phase deployment workflow. Use when designing, reviewing, hardening, or auditing any agent deployment — agent identity and credentials, tool/MCP access, sandboxing, memory persistence, multi-agent delegation, or security operations around agents.
Install
npx skills add Archive228/lab-skills --skill zero-trust-agentsgit clone --depth 1 https://github.com/Archive228/lab-skills.git /tmp/lab-skills
mkdir -p ~/.claude/skills
cp -r /tmp/lab-skills/skills/zero-trust-agents ~/.claude/skills/zero-trust-agentsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Zero-Trust Agent Deployment This skill gives you Anthropic's zero-trust operating procedure for deploying autonomous agents in an enterprise, distilled from the official eBook (May 2026). It covers the threat model specific to agents (prompt injection, tool poisoning, identity/privilege abuse, memory poisoning, supply chain), a three-tier control framework (Foundation / Enterprise / Advanced), an eight-phase implementation workflow, and rules for running security operations at the speed of AI-accelerated attackers. Core premise: trust nothing, verify everything, assume breach has already occurred — and remember that attackers running agents bring effectively unlimited patience at near-zero cost per attempt, so friction-only controls no longer count as security. ## When to use Use this skill when you are: - Designing or deploying an agent that has tool access (APIs, databases, filesystems, MCP servers), memory persistence, or multi-agent delegation. - Reviewing or auditing an existing agent deployment, its permissions, credentials, or MCP configuration. - Writing IAM policy, sandbox config, tool allowlists, or escalation/approval rules for agents. - Building agent-adjacent security operations: alert triage, SOAR playbooks, incident response for agent compromise. - Answering compliance questions for agents in regulated sectors (HIPAA, FINRA, GDPR, FedRAMP, EU AI Act all impose aligned requirements; US federal agencies must adopt Zero Trust by 2027).
Details
- Skill name
zero-trust-agents- Repository
- Archive228/lab-skills
- Path
skills/zero-trust-agents/SKILL.md- License
- MIT
- Repo updated
- 12 August 2026
FAQ
What does the Zero Trust Agents skill do?
Zero-trust security framework for deploying autonomous AI agents in an enterprise, distilled from Anthropic's official "Zero Trust for AI Agents" eBook: the Foundation/Enterprise/Advanced tier model, defenses against prompt injection, tool poisoning, memory poisoning and supply-chain attacks, and an 8-phase deployment workflow. Use when designing, reviewing, hardening, or auditing any agent deployment — agent identity and credentials, tool/MCP access, sandboxing, memory persistence, multi-agent delegation, or security operations around agents.
How do I install the Zero Trust Agents skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Archive228/lab-skills --skill zero-trust-agents. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Zero Trust Agents popular?
It lives in Archive228/lab-skills, which has 10 GitHub stars and 2 forks.
Related skills
Agent Design Fundamentals
10Archive228/lab-skills
Decision rules for whether to build an LLM agent and how to architect it, distilled from OpenAI's "A Practical Guide to Building Agents": build/no-build criteria, model selection, tool design, single-agent vs multi-agent orchestration (manager pattern vs decentralized handoffs), layered guardrails, and human-in-the-loop triggers. Use when designing, reviewing, or refactoring an agent system — before choosing an architecture, adding more agents, defining tools, or shipping an agent to production without guardrails.
Agent Evals
10Archive228/lab-skills
Build and maintain evaluation suites for AI agents: bootstrap 20-50 tasks from real failures, pick code-based vs model-based vs human graders by agent architecture (coding, conversational, research, computer-use), write unambiguous tasks with reference solutions, and keep suites alive via ownership and transcript reading. Use when creating evals from zero, adding graders or eval cases, debugging suspicious eval scores, or deciding pass@k vs pass^k metrics for an agent product.
Agent Failure Preflight
10Archive228/lab-skills
Pre-deployment failure-mode gate for agentic AI systems, distilled from Microsoft AI Red Team's Taxonomy of Failure Modes in Agentic AI Systems v2.0 (grounded in 12 months of red-team engagements). Run it before shipping or materially changing an agent — adding tools/MCP servers/plugins, enabling persistent memory, adding sub-agents or orchestration, enabling computer use, or expanding permissions — to verify concrete controls against memory poisoning, HitL bypass, goal hijacking, supply-chain compromise, session context contamination, capability disclosure, and multi-agent cascade failures.
Decisions Demo
5stagentic/stagentic-promptbook
A small demo of the stagentic-promptbook interpreter — helps the user pick between a few options when they can't decide. Trigger on "Stagentic, help me pick", "Stagentic, decide for me", or "Stagentic, pick one".
Workspace Os
9sidneyswift/skills
Use when a user wants to set up, scaffold, or reorganize a workspace or operating system for any domain; turn files, notes, or a prompt into a managed system; or make consequential work resumable across people, agents, and sessions.
Google Adk
9milistu/agent-skills
ALWAYS use this skill for any question involving Google ADK (Agent Development Kit). This includes: building or configuring agents (LlmAgent, SequentialAgent, LoopAgent, ParallelAgent, custom BaseAgent), writing function tools or connecting MCP/OpenAPI tools, managing sessions/state/memory, multi-agent routing and pipelines, before/after callbacks, streaming with Gemini Live API (run_live, LiveRequestQueue), deploying to Cloud Run or Vertex AI Agent Engine, evaluating agent behavior, A2A protocol, context caching/compression, grounding with Google Search. Trigger on any mention of 'adk', 'goog
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.