AWS wellarchitected: Add AGENTSEC01 memory security best-practice links
Summary
Adds three links to AGENTSEC01 best-practice pages on memory isolation and integrity controls, validating/sanitizing memory inputs, and monitoring hallucination propagation.
Security assessment
The added links point to security best practices for agent memory (isolation, input sanitization, integrity), so this is security documentation, but no specific vulnerability or incident is described in the diff.
Evidence
+[AGENTSEC01-BP02 Validate and sanitize memory inputs](./agentsec01-bp02.html)
Diff
diff --git a/wellarchitected/latest/agentic-ai-lens/agentsec01.md b/wellarchitected/latest/agentic-ai-lens/agentsec01.md index 1936060..87b1bf2 100644 --- a//wellarchitected/latest/agentic-ai-lens/agentsec01.md +++ b//wellarchitected/latest/agentic-ai-lens/agentsec01.md @@ -14,0 +15,3 @@ AGENTSEC01: How do you secure agentic memory and securely manage state between a +[AGENTSEC01-BP01 Implement memory isolation and integrity controls](./agentsec01-bp01.html) +[AGENTSEC01-BP02 Validate and sanitize memory inputs](./agentsec01-bp02.html) +[AGENTSEC01-BP03 Monitor for hallucination propagation](./agentsec01-bp03.html)