langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-21 20:05:30 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[PR #2753] docs: add security guide for RAG applications #2855

New Issue
Open
opened 2026-06-05 18:20:11 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 18:20:11 -04:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/2753
Author: @VedantMadane
Created: 2/21/2026
Status: 🔄 Open

Base: main ← Head: docs/rag-security-guide

📝 Commits (4)

  • 5d39775 docs: add security guide for RAG applications
  • 6663a9d Merge branch 'main' into docs/rag-security-guide
  • 25d7bca Merge branch 'main' into docs/rag-security-guide
  • 3ec3735 chore: refresh branch for mergeability check

📊 Changes

2 files changed (+67 additions, -0 deletions)

View changed files

📝 src/docs.json (+2 -0)
➕ src/oss/langchain/rag-security.mdx (+65 -0)

📄 Description

This PR adds a comprehensive security guide for RAG applications, covering indirect prompt injection and defense-in-depth recommendations (including content filtering with tools like ClawMoat).

This addresses the documentation needs discussed in langchain-ai/langchain#34780.

Key additions:

  • Threat model for Indirect Prompt Injection.
  • LangChain built-in defenses.
  • Defense-in-depth recommendations (Content filtering, Input/Output validation).
  • Practical code example integrating ClawMoat for document scanning.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/2753 **Author:** [@VedantMadane](https://github.com/VedantMadane) **Created:** 2/21/2026 **Status:** 🔄 Open **Base:** `main` ← **Head:** `docs/rag-security-guide` --- ### 📝 Commits (4) - [`5d39775`](https://github.com/langchain-ai/docs/commit/5d39775ee2c924a972e7179b9e0d46a8b52bf1e4) docs: add security guide for RAG applications - [`6663a9d`](https://github.com/langchain-ai/docs/commit/6663a9de17cabe7ab7ac788292db44a86df57003) Merge branch 'main' into docs/rag-security-guide - [`25d7bca`](https://github.com/langchain-ai/docs/commit/25d7bca111c53cc8a59060f32cddaffd61317654) Merge branch 'main' into docs/rag-security-guide - [`3ec3735`](https://github.com/langchain-ai/docs/commit/3ec37351e4fa56d4a996485c72f3bc69298ad0e1) chore: refresh branch for mergeability check ### 📊 Changes **2 files changed** (+67 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `src/docs.json` (+2 -0) ➕ `src/oss/langchain/rag-security.mdx` (+65 -0) </details> ### 📄 Description This PR adds a comprehensive security guide for RAG applications, covering indirect prompt injection and defense-in-depth recommendations (including content filtering with tools like ClawMoat). This addresses the documentation needs discussed in langchain-ai/langchain#34780. Key additions: - Threat model for Indirect Prompt Injection. - LangChain built-in defenses. - Defense-in-depth recommendations (Content filtering, Input/Output validation). - Practical code example integrating ClawMoat for document scanning. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:20:11 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#2855
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?