{ "schema": "aiblocks-page/1", "id": "agency-agentic-identity-trust", "type": "agent", "name": "AI agent identity designer", "summary": "Design how your AI agents prove who they are, what they may do and what they did, with a threat list, permission map and tamper-proof log.", "headline": "AI agent identity designer", "subhead": "Describe the AI agents in your system and what each one can do. It lists how an agent could be faked or overreach, then designs identity, permissions and an audit log. You get a design to review with a security engineer, not a live system.", "job": { "id": "secure-code", "name": "Keep your code secure" }, "level": "intermediate", "thinking": "high", "tested": true, "updated": "2026-11-03", "first_published": "2026-10-26", "inputs": [ { "type": "question", "required": true, "label": "Question", "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like" }, { "type": "source_text", "required": false, "label": "Source text", "what": "a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link" } ], "outputs": [ { "type": "plan", "required": true, "label": "Plan", "what": "a dated plan: what to do, in what order, with a decision rule for each step" }, { "type": "security_report", "required": true, "label": "Security report", "what": "the risks found in the code, ranked, each with a fix" } ], "you_give": [ "A list of your agents and what each one can do, in plain words.", "The risky actions, such as moving money, deploying code, changing data or sending messages.", "How the agents talk to each other and which tools you use, such as MCP or a REST API (optional)", "Who needs proof of what happened, such as an auditor, a customer or a regulator (optional)", "Rules you must meet, such as SOC 2 or financial rules (optional)" ], "you_get": [ "A threat list of how an agent could be faked, over-trusted or hide what it did", "An identity design for how each agent proves who it is, and how that proof ends or is cancelled", "A permission map showing what each agent may do and how a hand-off narrows it", "A design for an audit log that shows if anyone changed a record", "Deny rules and a list of tests that try to break the design" ], "use_when": [ "Your AI agents can spend money, send email, deploy code or call outside tools, and you need clear rules for who may do what.", "One agent hands work to another and you need proof that the first agent allowed it.", "An auditor, a customer or your boss asks how you know what an agent did and that the record was not changed.", "You are about to add agents to a product and want the identity design done before anyone writes code." ], "skip_when": [ "You need to decide if two customer or company records are the same one. Use the Identity graph designer.", "You want sign-in, single sign-on or passkeys for human users. Use the Identity and access engineer.", "You want finished code checked for bugs. Use the Application security reviewer.", "You want it to set up keys, servers or a live system. It writes the design. Your engineers build it and test it." ], "output_sample": { "input": [ "A list of your agents and what each can do", "The risky actions", "How the agents talk to each other and your tools (optional)", "Who needs proof, and any rules you must meet (optional)" ], "output": [ { "name": "Scope", "contains": "The agents, risky actions, readers of the record and rules the design was built for." }, { "name": "Threat list", "contains": "Each way an agent could be faked, over-trusted or hide an action, with the cost and the fix." }, { "name": "Identity design", "contains": "How each agent proves who it is, how long that lasts and how it is cancelled." }, { "name": "Permission and hand-off map", "contains": "What each agent may do, and the rule that hand-offs can only narrow powers." }, { "name": "Audit log design", "contains": "What is recorded for each action and how an edited record would be spotted." }, { "name": "Deny rules", "contains": "Conditions that stop an action, and what should raise an alert." }, { "name": "Test list", "contains": "Attacks to try against the built system, each with the result you should see." }, { "name": "Gaps and checks", "contains": "Missing facts and open choices, with who should decide each." } ] }, "output_shape": "SCOPE\n Agents | Risky actions | Who needs proof | Rules \n\nTHREAT LIST\n | | | \n\nIDENTITY DESIGN\n | | | \n\nPERMISSION AND HAND-OFF MAP\n | | \n\nAUDIT LOG DESIGN\n | | \n\nDENY RULES\n | | \n\nTEST LIST\n | \n\nGAPS AND CHECKS\n | | ", "how_to_use": [ "Download the pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.", "List your agents, what each can do and which actions are risky. Add how they talk to each other if you know. No code access is needed.", "Type \"Design identity and trust for these agents. Threat list first. Do not write code unless I ask. Mark anything you assume.\"", "Read the threat list first. Say which threats matter most, then ask it to run the design again.", "Give the design to a security engineer. Ask them to check every cryptography choice against current standards before anything is built.", "Build it yourself and run the test list. The AI does not run or test anything." ], "checks": [ "The result addresses your actual task and cites the evidence used.", "Examples, role-play experience and targets are kept separate from verified results.", "Claims of tests, memory, tool access or completed actions match what actually happened." ], "next": [ { "name": "Prompt injection defender", "url": "https://useaiblocks.com/skills/prompt-injection-defender", "why": "Prompt injection defender" }, { "name": "AI agent attack tester", "url": "https://useaiblocks.com/skills/ai-agent-attack-tester", "why": "AI agent attack tester" } ], "source": { "by": "Michael Sitarzewski and Agency Agents contributors", "repo": "msitarzewski/agency-agents", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/agentic-identity-trust.md", "licence": "MIT", "original_name": "Agentic Identity & Trust Architect", "commit": "b37b5bb33b78f2c1d6567d98e25ca818e3259219" }, "credits": [ { "title": "Agentic Identity & Trust Architect", "by": "Michael Sitarzewski and Agency Agents contributors", "url": "https://github.com/msitarzewski/agency-agents/blob/b37b5bb33b78f2c1d6567d98e25ca818e3259219/specialized/agentic-identity-trust.md", "used": "Original agent profile, preserved in references/source-agent.md; AI Blocks adds setup and review instructions." } ], "files": [ "LICENSE", "references/identity-graph-operator.md", "references/source-agent.md", "SETUP.md", "source.json" ], "links": { "page": "https://useaiblocks.com/agents/agency-agentic-identity-trust", "markdown": "https://useaiblocks.com/agents/agency-agentic-identity-trust.md", "json": "https://useaiblocks.com/agents/agency-agentic-identity-trust.json", "instructions": "https://useaiblocks.com/skills/agency-agentic-identity-trust/SKILL.md", "download": "https://useaiblocks.com/skills/agency-agentic-identity-trust.zip", "api_item": "https://useaiblocks.com/api/v1/items/agency-agentic-identity-trust", "api_document": "https://useaiblocks.com/api/v1/documents/agent/agency-agentic-identity-trust", "mcp": "https://useaiblocks.com/mcp" } }