EUVD-2026-81620
GHSA-p3qj-xm37-gqqf
Severity by source
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Unauthenticated network request-flood needs no special privilege or interaction once DistServe mode is enabled (AV:N/AC:L/PR:N); impact is availability-only via worker OOM, so C:N/I:N/A:H.
Primary rating from Vendor (VulnCheck).
CVSS VectorVendor: VulnCheck
Lifecycle Timeline
4DescriptionCVE.org
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate unreleased scheduler metadata and memory until the prefill worker is out-of-memory killed.
AnalysisAI
Memory exhaustion in InternLM LMDeploy through 0.17.0 can be triggered by unauthenticated remote attackers who send repeated completion requests to the proxy endpoint when the system runs in DistServe prefill/decode disaggregation mode. The proxy uses user-facing session IDs instead of internal scheduler keys, so scheduler sessions are never released, causing unbounded metadata and memory accumulation that eventually OOM-kills the prefill worker. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires the LMDeploy deployment to be running in DistServe prefill/decode disaggregation mode with the proxy endpoint reachable by the attacker; this is a non-default, specialized multi-worker serving topology, which is the primary limiting factor. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | This is a genuine but scope-limited availability threat, not an inflated high-CVSS score. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | No vendor-released patch has been identified at the time of analysis; track the GitHub issue https://github.com/InternLM/lmdeploy/issues/4967 and the VulnCheck advisory https://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-memory-exhaustion-via-session-id-mismatch for a fixed version. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, inventory all instances of InternLM LMDeploy up to version 0.17.0; if DistServe prefill/decode disaggregation mode is not required, disable it immediately; if it is required, restrict network access to the proxy endpoint to trusted IP addresses, enforce rate limiting on completion requests, and enable memory monitoring with OOM alerts. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t
BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser
pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi
The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica
OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph
pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.
Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301
In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse
Unauthenticated remote code execution affects Kestra OSS (the open-source event-driven orchestration platform) prior to
Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/
pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne
Share
External POC / Exploit Code
Leaving vuln.today