fix(deps): update dependency @langchain/community to v1 [security]

[renovate]

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package	Change	Age	Confidence
@langchain/community (source)	^0.3.22 → ^1.1.18

---

Warning

Some dependencies could not be looked up. Check the Dependency Dashboard for more information.

GitHub Vulnerability Alerts

CVE-2026-26019

Description

The RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawling to the same site as the base URL.

The implementation used String.startsWith() to compare URLs, which does not perform semantic URL validation. An attacker who controls content on a crawled page could include links to domains that share a string prefix with the target (e.g., https://example.com.attacker.com passes a startsWith check against https://example.com), causing the crawler to follow links to attacker-controlled or internal infrastructure.

Additionally, the crawler performed no validation against private or reserved IP addresses. A crawled page could include links targeting cloud metadata services (169.254.169.254), localhost, or RFC 1918 addresses, and the crawler would fetch them without restriction.

Impact

An attacker who can influence the content of a page being crawled (e.g., by placing a link on a public-facing page, forum, or user-generated content) could cause the crawler to:

• Fetch cloud instance metadata (AWS, GCP, Azure), potentially exposing IAM credentials and session tokens
• Access internal services on private networks (10.x, 172.16.x, 192.168.x)
• Connect to localhost services
• Exfiltrate response data via attacker-controlled redirect chains

This is exploitable in any environment where RecursiveUrlLoader runs on infrastructure with access to cloud metadata or internal services — which includes most cloud-hosted deployments.

Resolution

Two changes were made:

1. Origin comparison replaced. The startsWith check was replaced with a strict origin comparison using the URL API (new URL(link).origin === new URL(baseUrl).origin). This correctly validates scheme, hostname, and port as a unit, preventing subdomain-based bypasses.

2. SSRF validation added to all fetch operations. A new URL validation module (@langchain/core/utils/ssrf) was introduced and applied before every outbound fetch in the crawler. This blocks requests to:

   • Cloud metadata endpoints: 169.254.169.254, 169.254.170.2, 100.100.100.200, metadata.google.internal, and related hostnames
   • Private IP ranges: 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16, 127.0.0.0/8, 169.254.0.0/16
   • IPv6 equivalents: ::1, fc00::/7, fe80::/10
   • Non-HTTP/HTTPS schemes (file:, ftp:, javascript:, etc.)

Cloud metadata endpoints are unconditionally blocked and cannot be overridden.

Workarounds

Users who cannot upgrade immediately should avoid using RecursiveUrlLoader on untrusted or user-influenced content, or should run the crawler in a network environment without access to cloud metadata or internal services.

CVE-2026-27795

Summary

A redirect-based Server-Side Request Forgery (SSRF) bypass exists in RecursiveUrlLoader in @langchain/community. The loader validates the initial URL but allows the underlying fetch to follow redirects automatically, which permits a transition from a safe public URL to an internal or metadata endpoint without revalidation. This is a bypass of the SSRF protections introduced in 1.1.14 (CVE-2026-26019).

Affected Component

• Package: @langchain/community
• Component: RecursiveUrlLoader
• Configuration: preventOutside (default: true) is insufficient to prevent this bypass when redirects are followed automatically.

Description

RecursiveUrlLoader is a web crawler that recursively follows links from a starting URL. The existing SSRF mitigation validates the initial URL before fetching, but it does not re-validate when the request follows redirects. Because fetch follows redirects by default, an attacker can supply a public URL that passes validation and then redirects to a private network address, localhost, or cloud metadata endpoint.

This constitutes a “check‑then‑act” gap in the request lifecycle: the safety check occurs before the redirect chain is resolved, and the final destination is never validated.

Impact

If an attacker can influence content on a page being crawled (e.g., user‑generated content, untrusted external pages), they can cause the crawler to:

• Fetch cloud instance metadata (AWS, GCP, Azure), potentially exposing credentials or tokens
• Access internal services on private networks (10.x, 172.16.x, 192.168.x)
• Connect to localhost services
• Exfiltrate response data through attacker-controlled redirect chains

This is exploitable in any environment where RecursiveUrlLoader runs with access to internal networks or metadata services, which includes most cloud-hosted deployments.

Attack Scenario

1. The crawler is pointed at a public URL that passes initial SSRF validation.
2. That URL responds with a 3xx redirect to an internal target.
3. The fetch follows the redirect automatically without revalidation.
4. The crawler accesses the internal or metadata endpoint.

Example redirector:

https://302.r3dir.me/--to/?url=http://169.254.169.254/latest/meta-data/

Root Cause

• SSRF validation (validateSafeUrl) is only performed on the initial URL.
• Redirects are followed automatically by fetch (redirect: "follow" default), so the request can change destinations without additional validation.

Resolution

Upgrade to @langchain/community >= 1.1.18, which validates every redirect hop by disabling automatic redirects and re-validating Location targets before following them.

• Automatic redirects are disabled (redirect: "manual").
• Each 3xx Location is resolved and validated with validateSafeUrl() before the next request.
• A maximum redirect limit prevents infinite loops.

Reources

• Original SSRF fix (CVE-2026-26019): enforced origin comparison and added initial URL validation
• GHSA-gf3v-fwqg-4vh7

---

Release Notes

langchain-ai/langchainjs (@​langchain/community)

v1.1.18

Patch Changes

• #​9900 a9b5059 Thanks @​hntrl! - fix(core): update method signatures to use Partial<CallOptions> for options parameters

  Updated invoke, stream, generate, and generatePrompt method signatures across Runnable, BaseChatModel, and BaseLLM to correctly accept Partial<CallOptions> instead of full CallOptions. This aligns the implementation with the RunnableInterface specification and allows users to pass partial options (e.g., { signal: abortedSignal }) without TypeScript errors.

• #​9900 a9b5059 Thanks @​hntrl! - Improved abort signal handling for chat models:

  • Added ModelAbortError class in @langchain/core/errors that contains partial output when a model invocation is aborted mid-stream
  • invoke() now throws ModelAbortError with accumulated partialOutput when aborted during streaming (when using streaming callback handlers)
  • stream() throws a regular AbortError when aborted (since chunks are already yielded to the caller)
  • All provider implementations now properly check and propagate abort signals in both _generate() and _streamResponseChunks() methods
  • Added standard tests for abort signal behavior

v1.1.16

Patch Changes

• #​9830 70387a1 Thanks @​bracesproul! - fix: More undefined null errors and tests

• #​9679 a7c6ec5 Thanks @​christian-bromann! - feat(openai): elevate OpenAI image generation outputs to proper image content blocks

• #​9817 5e04543 Thanks @​Ashx098! - read error.status when response.status is absent to avoid retrying OpenAI SDK 4xx

• #​9819 40b4467 Thanks @​MrDockal! - Tool call content returns compacted json

• #​9815 17e30bd Thanks @​hntrl! - fix(core): respect tracingEnabled=false from RunTree when env tracing is enabled

v1.1.15

Patch Changes

• #​9781 230462d Thanks @​christian-bromann! - fix(core): preserve index and timestamp fields in _mergeDicts

v1.1.14

Patch Changes

• #​9990 d5e3db0 Thanks @​hntrl! - feat(core): Add SSRF protection module (@langchain/core/utils/ssrf) with utilities for validating URLs against private IPs, cloud metadata endpoints, and localhost.

  fix(community): Harden RecursiveUrlLoader against SSRF attacks by integrating validateSafeUrl and replacing string-based URL comparison with origin-based isSameOrigin from the shared SSRF module.

• Updated dependencies [d5e3db0, 6939dab, ad581c7]:

  • @​langchain/core@​1.1.21
  • @​langchain/openai@​1.2.7
  • @​langchain/classic@​1.0.17

v1.1.13

Patch Changes

• #​9777 3efe79c Thanks @​christian-bromann! - fix(core): properly elevate reasoning tokens

• #​9789 b8561c1 Thanks @​hntrl! - source JsonOutputParser content from text accessor

v1.1.12

Compare Source

Patch Changes

• #​9517 23be5af Thanks @​christian-bromann! - fix(@​langchain/core): add literal name type inference to tool()

v1.1.11

Compare Source

Patch Changes

• #​9753 a46a249 Thanks @​christian-bromann! - fix(core): allow shared object references in serialization

v1.1.10

Compare Source

Patch Changes

• #​9746 817fc9a Thanks @​bracesproul! - fix: _mergeDicts error when merging undefined values

v1.1.9

Compare Source

Patch Changes

• #​9725 56600b9 Thanks @​Orenoid! - fix(langchain): update merge logic for numeric values in mergeDicts

• #​9736 dc5c2ac Thanks @​hntrl! - fix(core): handle circular references in load

• #​9739 c28d24a Thanks @​christian-bromann! - fix(core): use getBufferString for message summarization

• #​9702 bfcb87d Thanks @​christian-bromann! - fix(core): improve interop with Zod

v1.1.8

Patch Changes

• #​9707 e5063f9 Thanks @​hntrl! - add security hardening for load

• #​9684 8996647 Thanks @​christian-bromann! - fix(core): document purpose of name in base message

v1.1.6

Compare Source

Patch Changes

• #​9835 adb3625 Thanks @​maahir30! - Use UTF-8 byte length for metadata fields

• Updated dependencies []:

  • @​langchain/classic@​1.0.10

v1.1.5

Compare Source

Patch Changes

• #​9641 005c729 Thanks @​christian-bromann! - fix(community/core): various security fixes

• #​7907 ab78246 Thanks @​jasonphillips! - fix(core): handle subgraph nesting better in graph_mermaid

• #​9589 8cc81c7 Thanks @​nathannewyen! - test(core): add test for response_metadata in streamEvents

• #​9644 f32e499 Thanks @​hntrl! - add bindTools to FakeListChatModel

• #​9508 a28d83d Thanks @​shubham-021! - Fix toFormattedString() to properly display nested objects in tool call arguments instead of [object Object]

• #​9165 2e5ad70 Thanks @​pawel-twardziak! - fix(mcp-adapters): preserve timeout from RunnableConfig in MCP tool calls

• #​9647 e456c66 Thanks @​hntrl! - handle missing parent runs in tracer to prevent LangSmith 400 errors

• #​9597 1cfe603 Thanks @​hntrl! - use uuid7 for run ids

v1.1.4

Compare Source

Patch Changes

• Updated dependencies [3efe79c]:
  • @​langchain/openai@​1.2.2
  • @​langchain/classic@​1.0.9

v1.1.3

Compare Source

Patch Changes

• #​9534 bd2c46e Thanks @​christian-bromann! - fix(@​langchain/core): update and bundle p-retry, ansi-styles, camelcase and decamelize dependencies

• #​9544 487378b Thanks @​hntrl! - fix tool chunk concat behavior (#​9450)

• #​9505 138e7fb Thanks @​chosh-dev! - feat: replace btoa with toBase64Url for encoding in drawMermaidImage

v1.1.2

Patch Changes

• #​9601 d79d2ff Thanks @​Orenoid! - feat(zhipuai): support tool calling in ChatZhipuAI

• Updated dependencies [13c9d5b, cc502e1, 75b3b90]:

  • @​langchain/openai@​1.2.1
  • @​langchain/classic@​1.0.8

v1.1.1

Patch Changes

• #​9495 636b994 Thanks @​gsriram24! - fix: use dynamic import for p-retry to support CommonJS environments

• #​9531 38f0162 Thanks @​hntrl! - add extras to tools

v1.1.0

Compare Source

Minor Changes

• #​9424 f17b2c9 Thanks @​hntrl! - add support for betas param

• #​9424 f17b2c9 Thanks @​hntrl! - add support for native structured output

Patch Changes

• #​9424 f17b2c9 Thanks @​hntrl! - bump sdk version

v1.0.7

Compare Source

Patch Changes

• #​9436 ca32dd7 Thanks @​sinedied! - Fix possible race condition in FileSystemChatMessageHistory

• #​8333 dc396c4 Thanks @​ejscribner! - community[minor]: Create CouchbaseQueryVectorStore

• Updated dependencies []:

  • @​langchain/classic@​1.0.5
  • @​langchain/openai@​1.1.3

v1.0.6

Patch Changes

• #​9434 f7cfece Thanks @​deepansh946! - Updated error handling behaviour of AgentNode

v1.0.5

Patch Changes

• #​9403 944bf56 Thanks @​christian-bromann! - improvements to toolEmulator middleware

• #​9388 831168a Thanks @​hntrl! - use profile.maxInputTokens in summarization middleware

• #​9393 f1e2f9e Thanks @​christian-bromann! - align context editing with summarization interface

• #​9427 bad7aea Thanks @​dqbd! - fix(langchain): add tool call contents and tool call ID to improve token count approximation

• #​9396 ed6b581 Thanks @​christian-bromann! - rename exit behavior from throw to error

v1.0.4

Patch Changes

• #​9326 3e0cab6 Thanks @​ayanyev! - Milvus vector store client: ignore auto-calculated fields in collection schema during payload validation

• Updated dependencies [415cb0b, a2ad61e, 34c472d]:

  • @​langchain/openai@​1.1.2
  • @​langchain/classic@​1.0.4

v1.0.3

Patch Changes

• Updated dependencies []:
  • @​langchain/google-gauth@​1.0.3

v1.0.2

Patch Changes

• Updated dependencies []:
  • @​langchain/google-gauth@​1.0.2

v0.3.59

v0.3.58

Compare Source

• fix: CVE 2025 12735 (#​9348) (#​9391) (68e6f49)
• fix(v0/anthropic): fix default temperature option (#​9362) (df3399f)
• chore(docs): Add redirect for v0.3 LangChain reference (#​9357) (006319a)
• chore(docs): Add redirect for v0.3 LangChain reference (c8ebe6d)
• Revert "fix: install missing system deps for vercel" (1e31844)
• fix: install missing system deps for vercel (028aa59)
• fix: add node-gyp for vercel build (594e334)
• fix(docs): Rewriting regex redirects (#​9313) (6bf4e90)
• fix(docs): Rewriting regex redirects (eebca00)
• fix(docs): Fix redirects (#​9312) (33e0bb6)
• fix(docs): Fix redirects (eff0ce1)
• fix(docs): get redirects to work (#​9302) (9df1dc3)
• fix(docs): get redirects to work (16fb7bd)
• fix(docs): Re-do redirects (#​9286) (247f577)
• fix(docs): combine redirects (8ff1728)
• fix(docs): split redirects (#​9283) (3695806)
• fix(docs): split redirects (9d948b0)
• chore(docs): Redirects for v0.3 docs (#​9219) (5f73e53)
• x (70eb7bc)
• x (06ebd78)
• fix (bb5b2de)
• fix (6540e07)
• fix (09f644d)
• Merge branch 'v0.3' into rd-v0.3 (68670cb)
• fix (2b2f009)
• fix (43cf1f3)
• fix (eb7c01f)
• fix (a8d782b)
• fix (934a548)
• v0.3 redirects (caba026)

v0.3.57

Compare Source

v0.3.56

Compare Source

v0.3.55

Compare Source

v0.3.54

Compare Source

v0.3.53

Compare Source

v0.3.52

Compare Source

v0.3.51

Compare Source

v0.3.50

Compare Source

v0.3.49

Compare Source

v0.3.48

Compare Source

v0.3.47

Compare Source

v0.3.46

Compare Source

v0.3.45

Compare Source

v0.3.44

Compare Source

v0.3.43

Compare Source

v0.3.42

Compare Source

v0.3.41

Compare Source

v0.3.40

Compare Source

v0.3.39

Compare Source

v0.3.38

Compare Source

v0.3.37

Compare Source

v0.3.36

Compare Source

v0.3.35

Compare Source

v0.3.34

Compare Source

v0.3.33

Compare Source

v0.3.32

Compare Source

v0.3.31

Compare Source

v0.3.30

Compare Source

v0.3.29

Compare Source

v0.3.28

Compare Source

v0.3.27

Compare Source

What's Changed

• Release 0.3.26 by @​benjamincburns in #​8185
• chore(mcp-adapters): migrate mcp-adapters package into LangChain monorepo by @​benjamincburns in #​8170
• feat!(weaviate): expose new features by updating weaviate client to v3.5.2 by @​dee-at-weaviate in #​8089
• fix(core, anthropic): handling for undefined tool outputs by @​shawnzhu in #​8141
• fix(openai): allow streaming o1 responses by @​Stadly in #​8175
• chore(genai): fix code sample in README by @​nuhmanpk in #​8214
• chore(community): fix docs typo in tavily_search_community by @​postbird in #​8199
• chore(docs): replace google analytics with google tag manager by @​danielrlambert3 in #​8174
• feat(aws): add performanceConfig by @​benjamincburns in #​8217
• chore(core): deprecate Runnable .bind, .map, and RunnableEach by @​benjamincburns in #​8187
• chore: stop using Runnable.bind by @​benjamincburns in #​8192
• fix(community): update ChromeAI to use the new window.LanguageModel by @​jtpio in #​8173
• release(weaviate): 0.2.0 by @​benjamincburns in #​8228
• feat(community): Return document ids when querying opensearch vector store by @​lucassmatos in #​8204
• release(community): 0.3.44 by @​benjamincburns in #​8229
• release(anthropic): 0.3.21 by @​benjamincburns in #​8230
• release(openai): 0.5.11 by @​benjamincburns in #​8231
• release(core): 0.3.57 by @​benjamincburns in #​8232

New Contributors

• @​dee-at-weaviate made their first contribution in #​8089
• @​shawnzhu made their first contribution in #​8141
• @​nuhmanpk made their first contribution in #​8214
• @​postbird made their first contribution in #​8199
• @​danielrlambert3 made their first contribution in #​8174
• @​lucassmatos made their first contribution in #​8204

Full Changelog: langchain-ai/langchainjs@0.3.26...0.3.27

v0.3.26

Compare Source

What's Changed

• Release 0.3.25 by @​benjamincburns in #​8169
• feat(utils/testing): add tool-call streaming support to FakeStreamingChatModel by @​RUPOJS in #​8112
• fix(community): mark Azure blob storage connection string as secrets by @​sinedied in #​8134
• fix(core): tracing perf improvements by @​benjamincburns in #​8176
• chore: bump smith version by @​benjamincburns in #​8180
• chore(core): deprecate RemoteRunnable by @​benjamincburns in #​8181
• fix(community): update generated secret map by @​benjamincburns in #​8182
• release(core): 0.3.56 by @​benjamincburns in #​8183
• release(community): 0.3.43 by @​benjamincburns in #​8184

Full Changelog: langchain-ai/langchainjs@0.3.25...0.3.26

v0.3.25

Compare Source

What's Changed

• feat(core): implement standard content blocks by @​benjamincburns in #​8062
• release(core): 0.3.48 by @​benjamincburns in #​8067
• feat(openai): implement standard content blocks by @​benjamincburns in #​8065
• feat(anthropic): implement standard content blocks by @​benjamincburns in #​8063
• feat(aws): implement standard content blocks by @​benjamincburns in #​8066
• chore(google): bump dep on core by @​benjamincburns in #​8064
• release(anthropic): 0.3.19 by @​benjamincburns in #​8069
• release(aws): 0.1.9 by @​benjamincburns in #​8070
• release(openai): 0.5.7 by @​benjamincburns in #​8071
• release(google): 0.2.5 by @​benjamincburns in #​8072
• docs: Update Google Analytics tag in docs by @​jacoblee93 in #​8075
• fix(core): Prevent DictPromptTemplate serialization from getting minified by @​jacoblee93 in #​8076
• release(core): 0.3.49 by @​jacoblee93 in #​8077
• fix(range_tests): fix latest dep range test for @​langchain/google-ver… by @​benjamincburns in #​8084
• feat(community): Add schema support for ensureTableInDatabase in typeorm vectorstore. by @​n1md7 in #​4504
• fix(langchain): improve output parsing in xml agent by @​jmlon in #​3975
• fix(community): export openapi util by @​schipiga in #​8037
• fix(langchain): fix react agent quote handling in JSON parsing by @​EfrosIonelu in #​7707
• chore(core) Document: add test checking pageContents empty string behavior by @​skarard in #​2836
• feat(tavily): use chunks per source arg by @​anadi45 in #​8081
• feat(core): support method field in StructuredPrompt by @​henryweng03 in #​6657
• feat(community): pgvector store: remove dependency with uuid-ossp extension by @​jouir in #​5014
• fix(community): Throw more descriptive errors for Ali toyi chat models by @​sinajia in #​5549
• fix(aws): Merge consecutive messages correctly in ChatBedrockConverse by @​michaelnchin in #​7978
• feat(openai): Response API support for reasoning summaries, stateful conversations, and

---

Configuration

📅 Schedule: Branch creation - "" (UTC), Automerge - At any time (no schedule defined).

🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.

♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.