CVE-2026-5497

Summary

vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the VideoMediaIO.load_base64() method. When processing video/jpeg data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.

Affected Software

Weaknesses

• CWE-400: CWE-400 Uncontrolled Resource Consumption

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: poc
  • Automatable: yes
  • Technical Impact: partial

Additional References

• https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4

vllm: vLLM: Denial of Service via unbounded video frame processing

Additional References

• https://access.redhat.com/security/cve/CVE-2026-5497
• https://bugzilla.redhat.com/show_bug.cgi?id=2487813
• https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json

References

• https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
• https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395

• ←Previous
• Next→