# LangGraph SDK has unsafe URL path construction

Advisory record · `GHSA-w39p-vh2g-g8g5`

- **Identifiers:** `GHSA-w39p-vh2g-g8g5` · `CVE-2026-48776` · `PYSEC-2026-2194` · `PYSEC-2026-2575`
- **State:** Confirmed
- **Severity:** CVSS 4.2 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-22](https://cwe.mitre.org/data/definitions/22.html) · [CWE-863](https://cwe.mitre.org/data/definitions/863.html)
- **Tags:** [Path traversal](https://agentprime.io/advisories/tag/path-traversal.md) · [Broken access control](https://agentprime.io/advisories/tag/access-control.md)
- **Published:** 25 Jun 2026
- **Updated:** 21 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 25 Jun 2026, 18:32 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `langgraph-sdk` (PyPI): affected `<0.3.15`; fixed in `0.3.15`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> LangGraph SDK (PyPI package langgraph-sdk) versions before 0.3.15 build request URLs by inserting caller-supplied identifiers without encoding them. An attacker who can influence identifier values passed to SDK methods could make a request reach a different resource or resource type than intended, potentially reading, modifying, or deleting resources beyond their authorization. Upgrade to langgraph-sdk 0.3.15 or later; until then, validate identifiers (for example as UUIDs) before passing them to the SDK. The source reports no known exploitation in the wild.

Written 5 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 4.2 Medium, CVSS 3.1: `CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0022, the 12th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:42 UTC: First seen by agentprime
- 31 Oct 2026, 14:42 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-w39p-vh2g-g8g5)

## Sources

- [GitHub Advisory Database: GHSA-w39p-vh2g-g8g5](https://github.com/advisories/GHSA-w39p-vh2g-g8g5)
- [OSV: GHSA-w39p-vh2g-g8g5](https://osv.dev/vulnerability/GHSA-w39p-vh2g-g8g5)
- <https://github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-48776>
- <https://github.com/advisories/GHSA-w39p-vh2g-g8g5>
- <https://github.com/langchain-ai/langgraph>
- <https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15>
- <https://github.com/pypa/advisory-database/tree/main/vulns/langgraph-sdk/PYSEC-2026-2575.yaml>
- <https://github.com/pypa/advisory-database/tree/main/vulns/langgraph/PYSEC-2026-2194.yaml>
- <https://pypi.org/project/langgraph-sdk>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-w39p-vh2g-g8g5>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-w39p-vh2g-g8g5/>. Everything for agents: <https://agentprime.io/llms.txt>.
