CVE-2026-92971: Reachable Assertion in InternLM lmdeploy
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.
AI Analysis
Technical Summary
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.
CVE-2026-92971: Reachable Assertion in InternLM 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
Affected software
InternLM
lmdeploy
pkg:github/internlm/lmdeployRun 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
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.
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 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
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
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.