# SGLang: Reachable Assertion via lora_path in LoRAManager enables remote Denial of Dervice

Advisory record · `GHSA-m2jr-x4gq-5rmj`

- **Identifiers:** `GHSA-m2jr-x4gq-5rmj` · `CVE-2026-10300` · `PYSEC-2026-3064`
- **State:** Confirmed
- **Severity:** CVSS 6.3 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-617](https://cwe.mitre.org/data/definitions/617.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 2 Jun 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 2 Jun 2026, 00:31 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `sglang` (PyPI): affected `<=0.5.10.post1`; no fixed version yet

## Machine-written summary

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

> SGLang versions up to and including 0.5.10.post1 are vulnerable. A remote attacker can manipulate the lora_path argument through the inference HTTP endpoint to trigger a reachable assertion, causing a denial of service; the source describes the attack as highly complex and difficult to exploit. No fixed version is listed. The source gives few other details.

Written 6 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

- 6.3 Medium, CVSS 4.0: `CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P`, from CNA (VulDB)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0037, the 31st percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:02 UTC: First seen by agentprime
- 31 Oct 2026, 15:02 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-m2jr-x4gq-5rmj)

## Sources

- [GitHub Advisory Database: GHSA-m2jr-x4gq-5rmj](https://github.com/advisories/GHSA-m2jr-x4gq-5rmj)
- [OSV: GHSA-m2jr-x4gq-5rmj](https://osv.dev/vulnerability/GHSA-m2jr-x4gq-5rmj)
- <https://nvd.nist.gov/vuln/detail/CVE-2026-10300>
- <https://github.com/sgl-project/sglang/issues/23141>
- <https://github.com/sgl-project/sglang/pull/25078>
- <https://github.com/sgl-project/sglang>
- <https://vuldb.com/cve/CVE-2026-10300>
- <https://vuldb.com/submit/828086>
- <https://vuldb.com/vuln/367593>
- <https://vuldb.com/vuln/367593/cti>

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-m2jr-x4gq-5rmj>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-m2jr-x4gq-5rmj/>. Everything for agents: <https://agentprime.io/llms.txt>.
