Skip to content
Noroxi
NVD / CVE Program· CNA GitHub_M

CVE-2026-33626: LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

Noroxi assessment

Priority: Plan (action score 44/100)

  • A ready-made attack module is public (Nuclei); exploiting it takes no special expertise.
  • Public proof-of-concept code exists (GitHub); there is no record of exploitation in the wild.
  • Probability of exploitation in the next 30 days: 45.2% (FIRST EPSS); higher than 98.7% of all records.
  • Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
  • According to CISA the attack is automatable: targets can be found by mass scanning.
  • No fixed version is recorded, but the references include a patch (commit or PR) link.

Add it to your regular patch cycle. See the fix and affected versions sections below.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.

HighCVSS 7.5 · v3.1—Proof of concept No fix recorded
Published
Apr 20, 2026
Updated
Oct 26, 2026
EPSS
45.2% · 98th percentile

Report tools

JSON

Action score

44

Plan

Add it to your regular patch cycle.

CVSS
30 / 40 · 7.5 / 10
CISA KEV
0 / 30 · Not listed
EPSS
14 / 30 · 45.2%

CISA SSVC decision

Exploitation
proof of concept
Automatable
yes
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
7.5
NVD has not scored this yet; the score shown is the CNA’s.

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

  • Not in KEV: no record of exploitation in the wild
  • Proof of concept exists, no weaponized module
  • No fixed version yet

If any of these changes, we'll tell you in the daily email digest.

Follow CVE-2026-33626

When you'll hear from us

  • when it enters CISA KEV
  • when exploit code appears or is weaponized
  • when the record is updated (including a fixed version)
  • when EPSS rises 20 points in a week

One daily email digest (06:00 UTC); connect a webhook for KEV listings and weaponized exploits instantly.

Your free account also gets you

Running WordPress? Scan your site free with WP Lens

  • Stack alerts: add the products and versions you run, get the new CVEs that affect them
  • Uptime monitoring: 1 site, instant email when it goes down
  • Add your domain: subdomains and takeover risk scanned every week (1 domain)
  • 10 scans an hour on the security tools (3 a day without an account), an API key and MCP
  • All your scans in one panel: findings, what changed in the last scan, a report per domain or per client (PDF, share link)
All free tools

Sign up with email · Have an account? Sign in

Free account, no card. Unfollow any time.

Don't want an account? Get "Exploited this week" by email every MondayDon't want an account? RSS feed for internlm records

Running WordPress? Scan your site free with WP Lens

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

VendorProduct
internlmlmdeploy

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • internlm lmdeploybefore 0.12.3

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • InternLM lmdeploy

    • < 0.12.3affected

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

EcosystemPackageAffected rangeFix
PyPIlmdeployup to and including 0.12.2—

Same product

internlm: all records

Other highest-scoring records for the same primary product.

  • CVE-2025-66455LMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py
    39Monitor
  • CVE-2025-59953LMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploy
    39Monitor
  • CVE-2026-119706LMDeploy 0.9.0 through 0.18.0 Unauthenticated RCE via /update_weights Pickle Deserialization
    37Monitor

Published before and after this one in the same product

  • ← EarlierCVE-2025-3163Apr 3, 2025 · InternLM LMDeploy conf.py open code injection
    19Monitor
  • ← EarlierCVE-2025-67729Dec 26, 2025 · lmdeploy vulnerable to Arbitrary Code Execution via Insecure Deserialization in torch.load()
    35Monitor
  • Later →CVE-2026-46432Jun 9, 2026 · LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization
    31Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

No fix version is recorded for this entry. Check the references for vendor advisories.

Exploit status

Proof of concept available

A public proof of concept or detection signature exists. Exploit knowledge is out there; don't delay patching.

Evidence

  • Nuclei detection template ×1
  • Proof-of-concept repository on GitHub ×1

Noroxi does not host or link to exploit code. Metasploit module names and Nuclei template ids are shown (names, not code); Exploit-DB entries and PoC repositories are given as counts only.

Public exploit evidence
SourceKindDate
Nuclei detection templateNuclei template CVE-2026-33626 —
Proof-of-concept repository on GitHubstars:02026-05-13

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

  1. Published
  2. First PoC+22 d
  3. TodayNov 8, 2026+202 d
EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

  • CVE-2026-6376492 days apartLMDeploy Server-Side Request Forgery via HTTP Redirect Bypass
    30Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
high · data can be read
Integrity
none
Availability
none
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality impact
High
Integrity impact
None
Availability impact
None

Weakness class (CWE)

CWE-918 · Server-Side Request Forgery (SSRF)

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

nvd-secondary

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

ATT&CK techniques

—

Change log

No changes recorded on tracked fields yet. Score, KEV, exploit maturity and fix status changes appear here.

References

Show all references (2 more)

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records