Skip to content

chore(deps): update dependency langchain-core to v1 [security] - autoclosed - #164

Closed
renovate-bot wants to merge 1 commit into
googleapis:mainfrom
renovate-bot:renovate/pypi-langchain-core-vulnerability
Closed

chore(deps): update dependency langchain-core to v1 [security] - autoclosed#164
renovate-bot wants to merge 1 commit into
googleapis:mainfrom
renovate-bot:renovate/pypi-langchain-core-vulnerability

Conversation

@renovate-bot

@renovate-bot renovate-bot commented Aug 31, 2026

Copy link
Copy Markdown
Contributor

ℹ️ Note

This PR body was truncated due to platform limits.

This PR contains the following updates:

Package Change Age Confidence
langchain-core (changelog) >=0.1.1, <1.0.0 → >=1.2.22, <1.2.23 age confidence

LangChain affected by SSRF via image_url token counting in ChatOpenAI.get_num_tokens_from_messages

CVE-2026-26013 / GHSA-2g6r-c272-w58r

More information

Details

Server-Side Request Forgery (SSRF) in ChatOpenAI Image Token Counting
Summary

The ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to trigger Server-Side Request Forgery (SSRF) attacks by providing malicious image URLs in user input.

Severity

Low - The vulnerability allows SSRF attacks but has limited impact due to:

  • Responses are not returned to the attacker (blind SSRF)
  • Default 5-second timeout limits resource exhaustion
  • Non-image responses fail at PIL image parsing
Impact

An attacker who can control image URLs passed to get_num_tokens_from_messages() can:

  • Trigger HTTP requests from the application server to arbitrary internal or external URLs
  • Cause the server to access internal network resources (private IPs, cloud metadata endpoints)
  • Cause minor resource consumption through image downloads (bounded by timeout)

Note: This vulnerability occurs during token counting, which may happen outside of model invocation (e.g., in logging, metrics, or token budgeting flows).

Details

The vulnerable code path:

  1. get_num_tokens_from_messages() processes messages containing image_url content blocks
  2. For images without detail: "low", it calls _url_to_size() to fetch the image and compute token counts
  3. _url_to_size() performs httpx.get(image_source) on any URL without validation
  4. Prior to the patch, there was no SSRF protection, size limits, or explicit timeout

File: libs/partners/openai/langchain_openai/chat_models/base.py

Patches

The vulnerability has been patched in langchain-openai==1.1.9 (requires langchain-core==1.2.11).

The patch adds:

  1. SSRF validation using langchain_core._security._ssrf_protection.validate_safe_url() to block:
    • Private IP ranges (RFC 1918, loopback, link-local)
    • Cloud metadata endpoints (169.254.169.254, etc.)
    • Invalid URL schemes
  2. Explicit size limits (50 MB maximum, matching OpenAI's payload limit)
  3. Explicit timeout (5 seconds, same as httpx.get default)
  4. Allow disabling image fetching via allow_fetching_images=False parameter
Workarounds

If you cannot upgrade immediately:

  1. Sanitize input: Validate and filter image_url values before passing messages to token counting or model invocation
  2. Use network controls: Implement egress filtering to prevent outbound requests to private IPs

Severity

  • CVSS Score: 3.7 / 10 (Low)
  • Vector String: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:L

References

This data is provided by the GitHub Advisory Database (CC-BY 4.0).

LangChain Core has Path Traversal vulnerabilites in legacy load_prompt functions

CVE-2026-34070 / GHSA-qh6h-p6c9-ff54

More information

Details

Summary

Multiple functions in langchain_core.prompts.loading read files from paths embedded in deserialized config dicts without validating against directory traversal or absolute path injection. When an application passes user-influenced prompt configurations to load_prompt() or load_prompt_from_config(), an attacker can read arbitrary files on the host filesystem, constrained only by file-extension checks (.txt for templates, .json/.yaml for examples).

Note: The affected functions (load_prompt, load_prompt_from_config, and the .save() method on prompt classes) are undocumented legacy APIs. They are superseded by the dumpd/dumps/load/loads serialization APIs in langchain_core.load, which do not perform filesystem reads and use an allowlist-based security model. As part of this fix, the legacy APIs have been formally deprecated and will be removed in 2.0.0.

Affected component

Package: langchain-core
File: langchain_core/prompts/loading.py
Affected functions: _load_template(), _load_examples(), _load_few_shot_prompt()

Severity

High

The score reflects the file-extension constraints that limit which files can be read.

Vulnerable code paths
Config key Loaded by Readable extensions
template_path, suffix_path, prefix_path _load_template() .txt
examples (when string) _load_examples() .json, .yaml, .yml
example_prompt_path _load_few_shot_prompt() .json, .yaml, .yml

None of these code paths validated the supplied path against absolute path injection or .. traversal sequences before reading from disk.

Impact

An attacker who controls or influences the prompt configuration dict can read files outside the intended directory:

  • .txt files: cloud-mounted secrets (/mnt/secrets/api_key.txt), requirements.txt, internal system prompts
  • .json/.yaml files: cloud credentials (~/.docker/config.json, ~/.azure/accessTokens.json), Kubernetes manifests, CI/CD configs, application settings

This is exploitable in applications that accept prompt configs from untrusted sources, including low-code AI builders and API wrappers that expose load_prompt_from_config().

Proof of concept
from langchain_core.prompts.loading import load_prompt_from_config

##### Reads /tmp/secret.txt via absolute path injection
config = {
    "_type": "prompt",
    "template_path": "/tmp/secret.txt",
    "input_variables": [],
}
prompt = load_prompt_from_config(config)
print(prompt.template)  # file contents disclosed

##### Reads ../../etc/secret.txt via directory traversal
config = {
    "_type": "prompt",
    "template_path": "../../etc/secret.txt",
    "input_variables": [],
}
prompt = load_prompt_from_config(config)

##### Reads arbitrary .json via few-shot examples
config = {
    "_type": "few_shot",
    "examples": "../../../../.docker/config.json",
    "example_prompt": {
        "_type": "prompt",
        "input_variables": ["input", "output"],
        "template": "{input}: {output}",
    },
    "prefix": "",
    "suffix": "{query}",
    "input_variables": ["query"],
}
prompt = load_prompt_from_config(config)
Mitigation

Update langchain-core to >= 1.2.22.

The fix adds path validation that rejects absolute paths and .. traversal sequences by default. An allow_dangerous_paths=True keyword argument is available on load_prompt() and load_prompt_from_config() for trusted inputs.

As described above, these legacy APIs have been formally deprecated. Users should migrate to dumpd/dumps/load/loads from langchain_core.load.

Credit

Severity

  • CVSS Score: 7.5 / 10 (High)
  • Vector String: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

References

This data is provided by the GitHub Advisory Database (CC-BY 4.0).

Release Notes

langchain-ai/langchain (langchain-core)

v1.2.18

v1.2.17

v1.2.16

v1.2.15

v1.2.14

v1.2.13

v1.2.12

v1.2.11

v1.2.10

v1.2.9

v1.2.8

v1.2.7

v1.2.6

v1.2.4

v1.2.3

v1.2.2

v1.2.1

v1.2.0

v1.1.3

v1.1.2

v1.1.1

v1.1.0

v1.0.7

v1.0.6

v1.0.5

v1.0.4

v1.0.3

v1.0.2

v1.0.0

v0.3.27

v0.3.26

v0.3.25

v0.3.24

v0.3.23

v0.3.22

v0.3.21

v0.3.20

v0.3.19

v0.3.18

v0.1.16

Compare Source

What's Changed

New Contributors

Full Changelog: langchain-ai/langchain@v0.1.15...v0.1.16

v0.1.15

Compare Source

What's Changed

New Contributors

Full Changelog: langchain-ai/langchain@v0.1.14...v0.1.15

v0.1.14

Compare Source

What's Changed

✂ Note

PR body was truncated to here.

Configuration

📅 Schedule: (UTC)

  • Branch creation
    • At any time (no schedule defined)
  • Automerge
    • At any time (no schedule defined)

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

♻ Rebasing: Never, 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.

@renovate-bot
renovate-bot requested review from a team as code owners August 31, 2026 20:51
@product-auto-label product-auto-label Bot added the api: cloudsql-mysql Issues related to the googleapis/langchain-google-cloud-sql-mysql-python API. label Aug 31, 2026
@dpebot

dpebot commented Aug 31, 2026

Copy link
Copy Markdown

/gcbrun

@renovate-bot renovate-bot changed the title chore(deps): update dependency langchain-core to v1 [security] chore(deps): update dependency langchain-core to v1 [security] - autoclosed Sep 7, 2026
@renovate-bot
renovate-bot deleted the renovate/pypi-langchain-core-vulnerability branch September 7, 2026 02:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@kgala2 kgala2

Labels

api: cloudsql-mysql Issues related to the googleapis/langchain-google-cloud-sql-mysql-python API.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@renovate-bot @dpebot @kgala2