From 481caf0125832c2b9027e94787c10ab4ea430556 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Tue, 4 Aug 2026 10:00:49 +0000 Subject: [PATCH] docs: drop production checklist from Secure Agent Design OSS CrewAI is typically used in operator-controlled environments. Remove the shipping checklist and soften production-required framing. Co-authored-by: Rip&Tear --- .../en/concepts/production-architecture.mdx | 2 +- .../agents/crafting-effective-agents.mdx | 2 +- .../en/guides/agents/secure-agent-design.mdx | 25 +++---------------- docs/edge/en/mcp/security.mdx | 2 +- 4 files changed, 6 insertions(+), 25 deletions(-) diff --git a/docs/edge/en/concepts/production-architecture.mdx b/docs/edge/en/concepts/production-architecture.mdx index 687911704..109b2cf9e 100644 --- a/docs/edge/en/concepts/production-architecture.mdx +++ b/docs/edge/en/concepts/production-architecture.mdx @@ -156,7 +156,7 @@ The new run gets a fresh `state.id` (auto-generated, or `inputs["id"]` if pinned ## Security -Agents with tools can take real-world actions. Before you ship, read **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)** — required guidance on trust boundaries, prompt injection, tool abuse, output validation, approval gates, limited delegation, and agent isolation. +Agents with tools can take real-world actions. Read **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)** for guidance on trust boundaries, prompt injection, tool abuse, output validation, approval gates, limited delegation, and agent isolation. ## Summary diff --git a/docs/edge/en/guides/agents/crafting-effective-agents.mdx b/docs/edge/en/guides/agents/crafting-effective-agents.mdx index 3dac30538..d6947a131 100644 --- a/docs/edge/en/guides/agents/crafting-effective-agents.mdx +++ b/docs/edge/en/guides/agents/crafting-effective-agents.mdx @@ -12,7 +12,7 @@ At the heart of CrewAI lies the agent - a specialized AI entity designed to perf This guide will help you master the art of agent design, enabling you to create specialized AI personas that collaborate effectively, think critically, and produce high-quality outputs tailored to your specific needs. -Shipping to production? Pair this guide with **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)** — required reading on trust boundaries, prompt injection, tool abuse, and approval gates. +Building agents that use tools or untrusted content? Pair this guide with **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)** — trust boundaries, prompt injection, tool abuse, and approval gates. ### Why Agent Design Matters diff --git a/docs/edge/en/guides/agents/secure-agent-design.mdx b/docs/edge/en/guides/agents/secure-agent-design.mdx index bf109fedd..15274e0c5 100644 --- a/docs/edge/en/guides/agents/secure-agent-design.mdx +++ b/docs/edge/en/guides/agents/secure-agent-design.mdx @@ -1,12 +1,12 @@ --- title: Secure Agent Design -description: Required reading for production agents — trusted vs untrusted inputs, prompt injection, tool abuse, output validation, approval gates, limited delegation, and agent isolation. +description: Design safer CrewAI agents — trusted vs untrusted inputs, prompt injection, tool abuse, output validation, approval gates, limited delegation, and agent isolation. icon: shield-halved mode: "wide" --- -**Required reading for production agents.** Agents with tools can take real-world actions. Treat every agent system as an untrusted code interpreter that can be steered by its inputs, until you prove otherwise with design controls. +Agents with tools can take real-world actions. Treat every agent system as an untrusted code interpreter that can be steered by its inputs, until you prove otherwise with design controls. ## Framework controls vs design patterns @@ -20,7 +20,7 @@ CrewAI gives you the **primitives** to enforce security (tool hooks, guardrails, | `human_input` / `@human_feedback` pauses for review | Trust boundaries in prompts and state | | `output_pydantic` validates schema shape | Treating other agents' output as untrusted until checked | -This guide is the checklist. Use it before you ship any agent that touches user data, external content, or side-effecting tools. +Use this guide whenever an agent touches user data, external content, or side-effecting tools — including local and operator-controlled setups. ## Why secure agent design matters @@ -299,25 +299,6 @@ class SecureOutreachFlow(Flow[PipelineState]): See [Production Architecture](/en/concepts/production-architecture). -## Production checklist - -Before shipping: - -- [ ] Trust boundaries documented for every input path (user, tools, RAG, other agents) -- [ ] Untrusted content labeled; secrets never in prompts; policy enforced outside the model -- [ ] Each agent has least-privilege tools and scoped credentials -- [ ] Destructive/side-effecting tools gated by hooks and/or HITL -- [ ] Policy hooks abort with `HookAborted` (other exceptions fail open) -- [ ] Tool arguments constrained in code (allowlists, schemas, SSRF/egress controls) -- [ ] Task guardrails and/or structured outputs on critical handoffs (schema ≠ policy) -- [ ] `allow_delegation=False` unless explicitly required (watch hierarchical managers) -- [ ] Read-heavy and write-heavy responsibilities isolated across agents or flow steps -- [ ] Memory/knowledge isolation verified (crew memory fallback understood) -- [ ] MCP/third-party servers reviewed under [MCP Security](/en/mcp/security) -- [ ] Production HITL uses a real review channel (not only console stdin) -- [ ] Logging/tracing enabled for tool calls, hook aborts, and approvals ([Tracing](/en/observability/tracing)) -- [ ] Basic injection/tool-abuse red-team cases exercised before release - ## Related guides diff --git a/docs/edge/en/mcp/security.mdx b/docs/edge/en/mcp/security.mdx index d2a667c9d..1779657c5 100644 --- a/docs/edge/en/mcp/security.mdx +++ b/docs/edge/en/mcp/security.mdx @@ -165,5 +165,5 @@ By understanding these security considerations and implementing best practices, These are by no means exhaustive, but they cover the most common and critical security concerns. The threats will continue to evolve, so it's important to stay informed and adapt your security measures accordingly. -For the broader production checklist — trust boundaries, prompt injection, tool abuse, approval gates, and agent isolation — see **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)**. +For broader secure agent design — trust boundaries, prompt injection, tool abuse, approval gates, and agent isolation — see **[Secure Agent Design](/edge/en/guides/agents/secure-agent-design)**.