docs: add Secure Agent Design production guide

Add a dedicated required-reading guide covering trust boundaries,
prompt injection (direct and indirect), tool abuse, output validation,
approval gates, limited delegation, and agent isolation. Register it
under Guides > Agents and cross-link from related production docs.

Co-authored-by: Rip&Tear <theCyberTech@users.noreply.github.com>
This commit is contained in:
Cursor Agent
2026-08-04 06:41:55 +00:00
parent b10c4ffcdc
commit 49bb6a83c1
5 changed files with 389 additions and 1 deletions

View File

@@ -98,7 +98,8 @@
"group": "Agents",
"icon": "user",
"pages": [
"edge/en/guides/agents/crafting-effective-agents"
"edge/en/guides/agents/crafting-effective-agents",
"edge/en/guides/agents/secure-agent-design"
]
},
{