Skip to main content

CVE-2026-92971: Reachable Assertion in InternLM lmdeploy

0
High
VulnerabilityCVE-2026-92971cvecve-2026-92971
Published: 09/17/2026 (09/17/2026, 13:43:15 UTC)
Source: CVE Database V5
Vendor/Project: InternLM
Product: lmdeploy

Description

CVE-2026-92971 is a reachable assertion vulnerability in InternLM's lmdeploy up to version 0.17.0. It allows unauthenticated attackers to crash the inference engine by submitting a specially crafted migration_request with an empty remote_block_ids list, triggering an AssertionError. This causes the engine loop to terminate and subsequent inference requests to fail, resulting in denial of service.

CVSS v4.0

Score 8.7high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
None
Vuln. Integrity
None
Vuln. Availability
High
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Affected software

InternLM

lmdeploy

Affected versions
>=0 <=0.17.0
GitHub Actionsmore threats →ai
internlm/lmdeploy
pkg:github/internlm/lmdeploy
Affected versions
>=0 <0.17.1

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/17/2026, 14:46:27 UTC

Technical Analysis

InternLM lmdeploy versions up to 0.17.0 contain a reachable assertion vulnerability in the DistServe decode migration loop. An attacker can send a migration_request with an empty remote_block_ids list, which triggers an AssertionError that crashes the inference engine's processing loop. This vulnerability allows unauthenticated attackers to cause a denial of service by terminating the inference engine, preventing further inference requests from being processed.

Potential Impact

The vulnerability enables unauthenticated attackers to cause a denial of service by crashing the inference engine, resulting in failure of subsequent inference requests. There is no indication of privilege escalation, data disclosure, or code execution beyond service disruption.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. No official fix or patch links are provided in the available data. Until a patch is available, consider implementing input validation or filtering to block migration_request messages with empty remote_block_ids if possible.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-09-17T13:23:54.594Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6aabfa1555bf5e2cf57f75ee

Added to database: 09/17/2026, 14:32:53 UTC

Last enriched: 09/17/2026, 14:46:27 UTC

Last updated: 09/17/2026, 14:46:27 UTC

Views: 5

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses