Answer in brief
CVE-2026-49121 records a Critical severity (CVSS 9.2) vulnerability in AI Tensor Engine for ROCm (AITER) 0.1.14 Unauthenticated RCE via MessageQueue.recv() Pickle Deserialization. The current sources do not mark it as known exploited. The current feed maps ROCm/aiter (generic), Red Hat/rhaiis/vllm-rocm-rhel9 (generic), Red Hat/rhaii/vllm-rocm-rhel9 (generic), Red Hat/rhelai3/bootc-azure-rocm-rhel9 (generic) and additional mapped packages. Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 9.2. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps ROCm/aiter (generic), Red Hat/rhaiis/vllm-rocm-rhel9 (generic), Red Hat/rhaii/vllm-rocm-rhel9 (generic), Red Hat/rhelai3/bootc-azure-rocm-rhel9 (generic) and additional mapped packages. Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| ROCm/aitergeneric | * | Not reported |
| Red Hat/rhaiis/vllm-rocm-rhel9generic | * | Not reported |
| Red Hat/rhaii/vllm-rocm-rhel9generic | * | Not reported |
| Red Hat/rhelai3/bootc-azure-rocm-rhel9generic | * | Not reported |
| Red Hat/rhelai3/bootc-rocm-rhel9generic | * | Not reported |
| Red Hat/rhoai/odh-vllm-rocm-rhel9generic | * | Not reported |
Published upstream
Jun 1, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Nov 8, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jul 6, 2026
AI Tensor Engine for ROCm (AITER) through 0.1.14 contains an unauthenticated remote code execution vulnerability in the MessageQueue.recv() function within shm_broadcast.py that allows unauthenticated remote attackers to execute arbitrary code by sending a malicious pickle payload to a ZMQ SUB socket with no authentication, HMAC, or format validation. Attackers who can reach the writer XPUB endpoint on the cluster network or supply a forged Handle with an attacker-controlled remote_subscribe_addr can deliver a crafted pickle payload that executes arbitrary code simultaneously as the inference worker process on every remote reader worker.
Quoted source text, attributed separately from HOL analysis.