In affected vLLM video-capable paths, a request could select the OpenPangu video backend and an extremely large num_frames value. Timestamp generation and list construction ran in Python before inference-level controls could bound the work. The researcher reproduced high CPU and memory consumption on a bounded test. A patch disables untrusted request-level…
Inspect the ClaimsCase · DiggingBeagle record
A client-supplied video sampling override could allocate excessive frames before model inference
In affected vLLM video-capable paths, a request could select the OpenPangu video backend and an extremely large num_frames value. Timestamp generation and list construction ran in Python before inference-level controls could bound the work.
Public disclosure: Nov 13, 2026
A requester can reach a video-capable completion or tokenization endpoint and pass multimodal media parameters.
At a glance
Unbounded preprocessor work is carried out before useful model work or a request-level compute budget is enforced.
Read the implicationsThe evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.
Limits and uncertaintyFull account
In affected vLLM video-capable paths, a request could select the OpenPangu video backend and an extremely large num_frames value. Timestamp generation and list construction ran in Python before inference-level controls could bound the work.
The researcher reproduced high CPU and memory consumption on a bounded test. A patch disables untrusted request-level multimodal overrides unless an operator explicitly enables their trusted mode. The larger projected allocations in the report were not all executed.
This is an admission and resource-budget failure, not a demonstrated GPU memory escape or a real production outage. Turning the trusted-override flag back on requires independent resource caps for the underlying sampler.
The evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.
Mechanism and trust boundary
- 01
Starting condition
A requester can reach a video-capable completion or tokenization endpoint and pass multimodal media parameters.
Boundary: precondition and attacker capability
- 02
Trust boundary crossed or evaluated
The researcher reproduced high CPU and memory consumption on a bounded test. A patch disables untrusted request-level multimodal overrides unless an operator explicitly enables their trusted mode. The larger projected allocations in the report were not all executed.
Boundary: mechanism
- 03
Observed consequence
Unbounded preprocessor work is carried out before useful model work or a request-level compute budget is enforced.
Boundary: observed effect and limitations
Claims & evidence
CLM-NOV15-VLLMVIDEO-MECHIn affected vLLM video-capable paths, a request could select the OpenPangu video backend and an extremely large num_frames value. Timestamp generation and list construction ran in Python before inference-level controls could bound the work. The researcher reproduced high CPU and memory consumption on a bounded test. A patch disables untrusted request-level multimodal overrides unless an operator explicitly enables their trusted mode. The larger projected allocations in the report were not all executed.supported
Basis: reported finding
- supportsvLLM video_backend override allows excessive frame samplingprimary disclosure
vLLM GHSA-894j-wg8m-63h8, video_backend OpenPangu override and num_frames request reproduction
CLM-NOV15-VLLMVIDEO-SCOPEThis is an admission and resource-budget failure, not a demonstrated GPU memory escape or a real production outage. Turning the trusted-override flag back on requires independent resource caps for the underlying sampler. The evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.supported
Basis: reported finding
- supportsvLLM video_backend override allows excessive frame samplingprimary disclosure
Primary disclosure: results, scope and limitations
Implications
Unbounded preprocessor work is carried out before useful model work or a request-level compute budget is enforced.
Controls and mitigations
- Reject untrusted backend and num_frames overrides by default; enforce absolute decode limits before timestamps and frame objects are allocated.
- Apply per-request CPU/memory/time limits at the serving process and test trust-request-mm-kwargs modes separately.
Unknowns and contradictions
- The evidence is bounded by the cited source and test setting. Broader incidence, other environments, and actual production consequences are not established merely by these observations.
Sources and citation
Material revision history
- Nov 15, 2026 · Canonical change recorded · new in release · revision 250