Kserve: kserve: server-side request forgery via malicious storageuri
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
Summary
KServe, a Kubernetes-based model serving platform, is affected. A user with permission to create or update InferenceService resources can supply a malicious storage URI that makes the storage-initializer component send outbound requests from inside the cluster, potentially exposing internal services and stealing node IAM role credentials.
Summarized by anthropic/claude-haiku-5.5. Verify details against the original sources.
Read the original description
A flaw was found in KServe. A namespace-scoped user with create/update permissions on InferenceService custom resources can exploit this vulnerability by providing a malicious `storageUri`. This Server-Side Request Forgery (SSRF) vulnerability allows the `storage-initializer` init container to issue arbitrary outbound HTTP/HTTPS requests from inside the cluster. This can lead to information disclosure, including credential theft for the node's Identity and Access Management (IAM) role or access to internal cluster services.
Timeline
- CVE published
- First seen by cve.now
Affected versions
- rhoai/odh-kserve-agent-rhel9
Version range not reported
- rhoai/odh-kserve-autogluon-server-rhel9
Version range not reported
- rhoai/odh-kserve-controller-rhel9
Version range not reported
- rhoai/odh-kserve-router-rhel9
Version range not reported
- rhoai/odh-kserve-storage-initializer-rhel9
Version range not reported