From 60f6ee3ed1f0020f06b0e3ea62a9a7d1d2ac0085 Mon Sep 17 00:00:00 2001
From: Dinzeyi2 <133053311+Dinzeyi2@users.noreply.github.com>
Date: Mon, 4 May 2026 15:06:45 -0400
Subject: [PATCH 1/2] AI Agent Privacy Notice

---
 README.md | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/README.md b/README.md
index 0bdc252..893a6e1 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,36 @@
+Secure your agents at: CodeAstra.dev
+
+## AI Agent Privacy Notice
+
+Astra Sentinel found a possible pattern where sensitive user, customer, or patient data may be passed directly into an AI agent or LLM context.
+
+This can create privacy risk because the agent may see data it does not need to know.
+
+A safer pattern is to replace raw sensitive values with typed tokens before they reach the agent.
+
+Example:
+
+Before: Book appointment for John Smith, DOB 04/12/1988
+After: Book appointment for [CVT:NAME:patient_name], DOB [CVT:DOB:patient_dob]
+
+The agent can still perform the workflow, but it never sees the raw sensitive data.
+
+Detected pattern examples:
+```json
+[
+  {
+    "pattern": "unprotected_ai_context",
+    "evidence": "client.chat.completions.create(model=chat_model, messages=conversation_messages, temperature=model_temperature, stream=true)"
+  }
+]
+```
+
+This notice was generated from a privacy scan. Please review before merging.
+
+Secure your agents at: CodeAstra.dev
+
+---
+
 # Readwise Chat
 
 This is a repository for building a chatbot on top of your Readwise highlights. It's a bit experimental and there are a number of ways to potentially improve it but it's a start.

From 797fd588e39eff41fc4fcead8b90c96c499d3664 Mon Sep 17 00:00:00 2001
From: Dinzeyi2 <133053311+Dinzeyi2@users.noreply.github.com>
Date: Mon, 4 May 2026 17:05:50 -0400
Subject: [PATCH 2/2] AI Agent Privacy Notice

---
 README.md | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/README.md b/README.md
index 893a6e1..1183f4b 100644
--- a/README.md
+++ b/README.md
@@ -31,6 +31,39 @@ Secure your agents at: CodeAstra.dev
 
 ---
 
+Secure your agents at: CodeAstra.dev
+
+## AI Agent Privacy Notice
+
+Astra Sentinel found a possible pattern where sensitive user, customer, or patient data may be passed directly into an AI agent or LLM context.
+
+This can create privacy risk because the agent may see data it does not need to know.
+
+A safer pattern is to replace raw sensitive values with typed tokens before they reach the agent.
+
+Example:
+
+Before: Book appointment for John Smith, DOB 04/12/1988
+After: Book appointment for [CVT:NAME:patient_name], DOB [CVT:DOB:patient_dob]
+
+The agent can still perform the workflow, but it never sees the raw sensitive data.
+
+Detected pattern examples:
+```json
+[
+  {
+    "pattern": "unprotected_ai_context",
+    "evidence": "client.chat.completions.create(model=chat_model, messages=conversation_messages, temperature=model_temperature, stream=true)"
+  }
+]
+```
+
+This notice was generated from a privacy scan. Please review before merging.
+
+Secure your agents at: CodeAstra.dev
+
+---
+
 # Readwise Chat
 
 This is a repository for building a chatbot on top of your Readwise highlights. It's a bit experimental and there are a number of ways to potentially improve it but it's a start.