docs: rewrite Secure Agent Design in plain reference style

Rewrite the guide in short factual prose aligned with actual CrewAI
behavior: kickoff vs Task/Crew controls, Agent.guardrail kickoff-only,
global CrewBase hooks, tool HookAborted scope, fail-open hooks, and
memory fallback. Add ar/ko/pt-BR pages and nav entries.

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
This commit is contained in:
Cursor Agent
2026-08-12 06:17:44 +00:00
parent da28681f04
commit fbd25dfd48
18 changed files with 1121 additions and 139 deletions

View File

@@ -12141,7 +12141,8 @@
"group": "Agentes",
"icon": "user",
"pages": [
"edge/pt-BR/guides/agents/crafting-effective-agents"
"edge/pt-BR/guides/agents/crafting-effective-agents",
"edge/pt-BR/guides/agents/secure-agent-design"
]
},
{
@@ -23419,7 +23420,8 @@
"group": "에이전트 (Agents)",
"icon": "user",
"pages": [
"edge/ko/guides/agents/crafting-effective-agents"
"edge/ko/guides/agents/crafting-effective-agents",
"edge/ko/guides/agents/secure-agent-design"
]
},
{
@@ -35081,7 +35083,8 @@
"group": "الوكلاء",
"icon": "user",
"pages": [
"edge/ar/guides/agents/crafting-effective-agents"
"edge/ar/guides/agents/crafting-effective-agents",
"edge/ar/guides/agents/secure-agent-design"
]
},
{