Unsafe Deserialization in AI Tensor Engine for ROCm (CVE-2026-49121)
Summary
Vulnerability in AI Tensor Engine for ROCm (CVE-2026-49121). Successful exploitation can lead to full system takeover.
Original description
The description as published by the source.
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.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-49121 has been found in AI Tensor Engine for ROCm.
Successful exploitation can lead to full system takeover. CVSS score: 8.1/10.
What to do: apply the vendor's official patched release.
If unsure, ask your IT team or search "AI Tensor Engine for ROCm CVE-2026-49121" on the vendor's site.
CVE-2026-49121 (AI Tensor Engine for ROCm) — CWE-502 / CVSS v3 8.1
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Unsafe deserialization (CWE-502) exists in AI Tensor Engine for ROCm.
Check the vendor advisory for the affected versions of AI Tensor Engine for ROCm.
Severity: High (CVSS 8.1/10). Successful exploitation can lead to full system takeover.
Update to the patched release per vendor advisory.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Audit SBOM/dependencies to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
Audit SBOM/dependencies for affected components.資産台帳・SBOM・依存マニフェストで AI Tensor Engine for ROCm を使っているサービスとバージョンを洗い出す。
-
2Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
References
- advisory vulncheck.com
- advisory nvd.nist.gov
- advisory access.redhat.com
- advisory github.com
- package github.com
- report github.com
- report github.com
- report bugzilla.redhat.com
- web github.com
- web security.access.redhat.com