.NET: Add security warnings to xml comments for core components

[westey-m]

Motivation and Context

#3236

Description

• Add security warnings to xml comments for core components

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the Contribution Guidelines
• All unit tests pass, and I have added new tests where possible
• Is this a breaking change? If yes, add "[BREAKING]" prefix to the title of the PR.

[Copilot]

Pull request overview

Adds security-focused XML documentation warnings to core Agent Framework .NET components to help developers understand trust boundaries (external services, storage backends, tools) and common LLM-related risks (prompt injection, sensitive data exposure).

Changes:

• Add “Security considerations” sections to core abstractions (agents, sessions, context providers, chat history providers).
• Add targeted security notes to key implementations (Cosmos chat history, vector-store chat history memory, Mem0 provider, text search provider).
• Add telemetry-related sensitive data capture warning to OpenTelemetry integration.

Reviewed changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
dotnet/src/Microsoft.Agents.AI/TextSearchProvider.cs	Documents prompt-injection and untrusted-input risks when injecting external search results.
dotnet/src/Microsoft.Agents.AI/OpenTelemetryAgent.cs	Warns about PII/sensitive content exposure when enabling message-content telemetry.
dotnet/src/Microsoft.Agents.AI/Memory/ChatHistoryMemoryProvider.cs	Documents indirect prompt injection/PII risks for vector-store-backed memory retrieval and trace logging.
dotnet/src/Microsoft.Agents.AI/ChatClient/ChatClientAgent.cs	Adds class-level security remarks about trust boundaries, tool invocation, and output sanitization.
dotnet/src/Microsoft.Agents.AI.Mem0/Mem0Provider.cs	Documents external service trust, PII, prompt injection, and trace logging considerations for Mem0.
dotnet/src/Microsoft.Agents.AI.CosmosNoSql/CosmosChatHistoryProvider.cs	Documents PII retention/TTL, compromised store risks, and auth best practices for Cosmos DB.
dotnet/src/Microsoft.Agents.AI.Abstractions/ChatHistoryProvider.cs	Adds security guidance for untrusted loaded messages and secure storage of chat history.
dotnet/src/Microsoft.Agents.AI.Abstractions/AgentSession.cs	Adds guidance for secure session serialization and cautions about persisting sensitive StateBag data.
dotnet/src/Microsoft.Agents.AI.Abstractions/AIContextProvider.cs	Documents risks of providers injecting high-trust roles and unvalidated external content into context.
dotnet/src/Microsoft.Agents.AI.Abstractions/AIAgent.cs	Adds top-level agent security remarks and session/message handling cautions.