live wire
▸PLATFORM · Quay.io push and pull operations hit intermittent 500 errors during maintenanceRed Hat status▸INTEGRATION · Apache Camel exposes incident and web search as parallel tools for a local agentApache Camel▸AI · Red Hat makes confidential GPU AI GA and previews VM-isolated Agent Sandbox (Aug. 4)Red Hat Blog▸SECURITY · Red Hat fixes Important MariaDB GIS memory-corruption flaw in Hardened ImagesRed Hat Product Security▸SECURITY · Red Hat restores CVE pages after a CWE dependency outage; monitoring continuesRed Hat status▸PLATFORM · Red Hat implements a fix for docs.redhat.com degradation and begins monitoringRed Hat status▸AI · vLLM combines PCP, DCP and host-memory offload to serve 1M-token GLM-5.3 contextsvLLM▸AI · vLLM ships day-zero MiniMax-M3.1-Flash support across NVIDIA and AMD GPUsvLLM▸SECURITY · Red Hat revokes compromised eMudhra certificates across RHEL and OpenShift trust storesRed Hat Product Security▸SECURITY · Red Hat rates PHP2Shell request-handling flaws Important; fixes are rolling outRed Hat Product Security▸AI · IBM maps GPU observability and FinOps controls across OpenShift clustersIBM Community▸IDENTITY · Red Hat shows Data Grid authentication through Keycloak 26 on OpenShiftRed Hat Developer▸AI · Red Hat layers tenant isolation, tool authorization and rate limits onto MCP gatewaysRed Hat Developer▸DATA · Red Hat maps direct LDAP and LDAPS authentication for Data Grid on OpenShiftRed Hat Developer▸PLATFORM · Quay.io push and pull operations hit intermittent 500 errors during maintenanceRed Hat status▸INTEGRATION · Apache Camel exposes incident and web search as parallel tools for a local agentApache Camel▸AI · Red Hat makes confidential GPU AI GA and previews VM-isolated Agent Sandbox (Aug. 4)Red Hat Blog▸SECURITY · Red Hat fixes Important MariaDB GIS memory-corruption flaw in Hardened ImagesRed Hat Product Security▸SECURITY · Red Hat restores CVE pages after a CWE dependency outage; monitoring continuesRed Hat status▸PLATFORM · Red Hat implements a fix for docs.redhat.com degradation and begins monitoringRed Hat status▸AI · vLLM combines PCP, DCP and host-memory offload to serve 1M-token GLM-5.3 contextsvLLM▸AI · vLLM ships day-zero MiniMax-M3.1-Flash support across NVIDIA and AMD GPUsvLLM▸SECURITY · Red Hat revokes compromised eMudhra certificates across RHEL and OpenShift trust storesRed Hat Product Security▸SECURITY · Red Hat rates PHP2Shell request-handling flaws Important; fixes are rolling outRed Hat Product Security▸AI · IBM maps GPU observability and FinOps controls across OpenShift clustersIBM Community▸IDENTITY · Red Hat shows Data Grid authentication through Keycloak 26 on OpenShiftRed Hat Developer▸AI · Red Hat layers tenant isolation, tool authorization and rate limits onto MCP gatewaysRed Hat Developer▸DATA · Red Hat maps direct LDAP and LDAPS authentication for Data Grid on OpenShiftRed Hat Developer
upstreambeat.ai
releaseSECURITY

Podman 6.1.3 closes a sandbox bypass by removing checkpoint images from podman run

The security fix is deliberately breaking: checkpoint images can no longer override user-requested container isolation through the normal run path.

Podman 6.1.3 blocks checkpoint images from overriding sandbox settings.
Side by side: what changed
By The Release Desk· Sep 29, 2026the quick take — two AI hosts go live when you do

Podman 6.1.3 removes support for running container checkpoint images through podman run, closing CVE-2026-94603. The project describes the change as both a security fix and a breaking change because the affected checkpoint path could silently replace sandbox settings supplied by the user.

What changed

Podman added OCI distribution of container checkpoints in version 4.4.0, allowing a checkpoint to be pulled from a registry and launched with podman run. Podman identifies those artifacts through the io.podman.annotations.checkpoint.runtime.name image annotation.

The project's security advisory says that once this annotation was present, checkpoint configuration controlled how the container was created. User-provided restrictions could be ignored: the advisory gives podman run --cap-drop=ALL as an example where the checkpoint could instead restore a different capability set. The maintainers concluded that treating checkpoints like ordinary runnable images was inherently unsafe and reverted the feature.

Who it affects

Teams that pull images from registries and depend on command-line sandbox controls should treat the update as security-relevant. The risk is concentrated in images carrying the checkpoint-runtime annotation, but the normal podman run interface did not distinguish that security model clearly enough for callers to rely on their requested restrictions.

The release also affects legitimate workflows that distributed checkpoints as OCI images and launched them with podman run. Podman 6.1.3 intentionally removes that behavior rather than trying to preserve compatibility.

What to do

Users on the 6.1 line should update to 6.1.3 and test any checkpoint-transfer workflow against the removal. Where an immediate update is not possible, the advisory's workaround is to scan pulled images for io.podman.annotations.checkpoint.runtime.name and reject images carrying it. The advisory also warns that Podman cannot currently perform that scan and rejection automatically, so the check must sit elsewhere in the image-admission or pull process.

sources

Filed by The Release Desk. Corrections: desk@upstreambeat.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.

    more from the desk