Add security comments for GetResponseAsync/GetStreamingResponseAsync

src/Libraries/Microsoft.Extensions.AI.Abstractions/ChatCompletion/IChatClient.cs

@@ -33,6 +33,11 @@ public interface IChatClient : IDisposable
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
+    /// <remarks>
+    /// Applications must consider the risks of prompt injection attacks, data sizes, and the number of messages
+    /// sent to the underlying provider or returned from it. Unless a specific <see cref="IChatClient"/> implementation
+    /// explicitly documents safeguards for these concerns, the application is expected to implement appropriate protections.
+    /// </remarks>
     /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#request-a-chat-response">Request a chat response.</related>
     Task<ChatResponse> GetResponseAsync(
         IEnumerable<ChatMessage> messages,
@@ -45,6 +50,11 @@ Task<ChatResponse> GetResponseAsync(
     /// <param name="cancellationToken">The <see cref="CancellationToken"/> to monitor for cancellation requests. The default is <see cref="CancellationToken.None"/>.</param>
     /// <returns>The response messages generated by the client.</returns>
     /// <exception cref="ArgumentNullException"><paramref name="messages"/> is <see langword="null"/>.</exception>
+    /// <remarks>
+    /// Applications must consider the risks of prompt injection attacks, data sizes, and the number of messages
+    /// sent to the underlying provider or returned from it. Unless a specific <see cref="IChatClient"/> implementation
+    /// explicitly documents safeguards for these concerns, the application is expected to implement appropriate protections.
+    /// </remarks>
     /// <related type="Article" href="https://learn.microsoft.com/dotnet/ai/microsoft-extensions-ai#request-a-streaming-chat-response">Request a streaming chat response.</related>
     IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
         IEnumerable<ChatMessage> messages,

src/Libraries/Microsoft.Extensions.AI.AzureAIInference/AzureAIInferenceChatClient.cs

@@ -73,6 +73,20 @@ public AzureAIInferenceChatClient(ChatCompletionsClient chatCompletionsClient, s
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public async Task<ChatResponse> GetResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
     {
@@ -128,6 +142,20 @@ public async Task<ChatResponse> GetResponseAsync(
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {

src/Libraries/Microsoft.Extensions.AI.Ollama/OllamaChatClient.cs

@@ -80,6 +80,20 @@ public JsonSerializerOptions ToolCallJsonSerializerOptions
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public async Task<ChatResponse> GetResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
     {
@@ -118,6 +132,20 @@ public async Task<ChatResponse> GetResponseAsync(
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public async IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, [EnumeratorCancellation] CancellationToken cancellationToken = default)
     {

src/Libraries/Microsoft.Extensions.AI.OpenAI/OpenAIChatClient.cs

@@ -68,6 +68,20 @@ public OpenAIChatClient(ChatClient chatClient)
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public async Task<ChatResponse> GetResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
     {
@@ -83,6 +97,20 @@ public async Task<ChatResponse> GetResponseAsync(
     }
 
     /// <inheritdoc />
+    /// <remarks>
+    /// <para>
+    /// No prompt injection defense is performed by default for data within <paramref name="messages"/>.
+    /// Applications are expected to implement guards against prompt injection attacks as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on data sizes sent to the underlying provider or returned from it
+    /// by default. Applications are expected to apply data size limits as needed.
+    /// </para>
+    /// <para>
+    /// There are no limits or restrictions imposed on the number of messages sent to the underlying provider or returned from
+    /// it by default. Applications are expected to apply rate limits on a per-user or per-session basis as needed.
+    /// </para>
+    /// </remarks>
     public IAsyncEnumerable<ChatResponseUpdate> GetStreamingResponseAsync(
         IEnumerable<ChatMessage> messages, ChatOptions? options = null, CancellationToken cancellationToken = default)
     {