diff --git a/pipeline/test_loop_engineering_meta_prompt.py b/pipeline/test_loop_engineering_meta_prompt.py
index 95f2751..7ac9c21 100644
--- a/pipeline/test_loop_engineering_meta_prompt.py
+++ b/pipeline/test_loop_engineering_meta_prompt.py
@@ -23,6 +23,12 @@ def test_loop_engineering_meta_prompt_locks_safety_fields():
         "Team manages agents",
         "vault/proxy credential injection",
         "YouTube `hLUGXO5DSpo`",
+        "External research anchors",
+        "NVIDIA Secure Agent Workspace",
+        "Infisical Agent Vault",
+        "Anthropic agent evals",
+        "OWASP AI Agent Security Cheat Sheet",
+        "signed-action-only",
         "Model Workspace Protocol",
         "00-intake/",
         "40-ship/",
diff --git a/plans/meta-prompts/loop_engineering.md b/plans/meta-prompts/loop_engineering.md
index 2b975c8..135bd16 100644
--- a/plans/meta-prompts/loop_engineering.md
+++ b/plans/meta-prompts/loop_engineering.md
@@ -85,6 +85,19 @@ Every autonomous work-agent plan must include:
 
 Reference: Latent Space, "The Blueprint for Autonomous Work Agents" with Gavriel Cohen / NanoClaw (YouTube `hLUGXO5DSpo`).
 
+## External research anchors
+
+Ground agent plans against external production guidance, not just video notes:
+
+- NVIDIA Secure Agent Workspace: always-on agents need a managed workspace with credential proxy, enterprise tool access, governance, and runtime controls.
+- Infisical Agent Vault: secrets stay in the vault and requests receive credentials through a proxy; agents must not hold raw secrets.
+- Anthropic agent evals: judge trajectories and environment outcomes, not just final answers.
+- OWASP AI Agent Security Cheat Sheet: treat prompt injection, memory poisoning, tool abuse, sandboxing, and access control as first-class risks.
+
+These anchors support TAC's local rule: deploy remains signed-action-only through `git-proxy:8099/deploy`; do not reintroduce raw command deploy paths.
+
+References: NVIDIA Secure Agent Workspace (`docs.nvidia.com/enterprise-reference-architectures/secure-agent-workspace-reference-design`), Infisical Agent Vault (`infisical.com/blog/agent-vault-the-open-source-credential-proxy-and-vault-for-agents`), Anthropic "Demystifying evals for AI agents" (`anthropic.com/engineering/demystifying-evals-for-ai-agents`), OWASP AI Agent Security Cheat Sheet (`cheatsheetseries.owasp.org/cheatsheets/AI_Agent_Security_Cheat_Sheet.html`).
+
 ## Model Workspace Protocol note
 
 For sequential workflows with human review between stages, prefer folder-structured orchestration before multi-agent framework code. The Model Workspace Protocol pattern treats numbered folders as stages, markdown files as role/context carriers, and local scripts as the boring mechanical layer.