Advisory

PYSEC-2026-3938

Also known as: CVE-2026-73557, GHSA-pr7f-p5mw-fc87

Summary

vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts

Details

Executive Summary

The follow-up protection for CVE-2025-62164 is incomplete at vLLM revision 26587f9519e22a5c4549ead7595ad9ca3229c4fd. It wraps serialized prompt-embedding reconstruction and dense conversion in torch.sparse.check_sparse_tensor_invariants(), but PyTorch 2.11.0 implements that context with save/enable/restore operations over process-global state. Two prompt-embedding parts in one /v1/chat/completions request are gathered concurrently on the event loop's default executor. When one context exits before the other loads its tensor, it can restore the global flag to False while the second part remains inside its guard.

In a deterministic run against hash-verified source from the affected revision, the actual target loader rejected an invalid sparse payload as a negative control. The frozen chat tracker then scheduled benign and malicious parts on distinct asyncio_0 and asyncio_1 threads. The benign context exited, the malicious loader observed the invariant flag disabled, and torch.load(weights_only=True) reconstructed indices [[10], [10]] for a declared shape of [3, 3]. The run intercepted the target's to_dense() call before it operated on the invalid tensor.

This primary trigger requires --enable-prompt-embeds, which is default-off, but it does not require renderer_num_workers > 1, a multimodal model, or --enable-mm-embeds. API authentication is optional in the stock server: middleware is installed only when CLI or environment API keys are supplied.

The lab proves bypass of the follow-up guard, invalid sparse reconstruction, and guarded-sink reachability. Crash and memory-corruption consequences are conditional on the behavior documented by the published CVE.

Background

CVE-2025-62164 / GHSA-mrw7-hf4f-83pf concerns client-controlled serialized prompt_embeds reaching torch.load(weights_only=True) and an invalid sparse tensor reaching to_dense(). The advisory attributes memory corruption, denial of service, and potential code execution to that historical unsafe operation.

The remediation chronology matters for duplicate handling:

This report therefore does not present the malformed sparse payload or to_dense() sink as new. It reports a distinct concurrency root cause and trigger: unsynchronized save/enable/restore of the process-global follow-up guard, reachable through the later multi-part chat scheduler.

The affected revision pins PyTorch 2.11.0 in pyproject.toml:10.

Vulnerability Details

The target's safe_load_prompt_embeds performs the guarded operation in vllm/renderers/embed_utils.py:16-39:

with torch.sparse.check_sparse_tensor_invariants():
    tensor = torch.load(
        BytesIO(pybase64.b64decode(embed, validate=True)),
        weights_only=True,
        map_location=torch.device("cpu"),
    )
    if not isinstance(tensor, torch.Tensor):
        raise VLLMValidationError(...)
    tensor = tensor.to_dense()

The context is not request-local. With the global flag initially disabled, we can describe the verified interleaving:

  1. Benign part A enters, saves False, and enables the flag.
  2. Malicious part B enters, saves True, and leaves the flag enabled.
  3. A completes its load and exits, restoring its saved False value.
  4. B remains lexically inside its context but observes the actual global flag as False.
  5. B's torch.load(..., weights_only=True) reconstructs the malformed sparse tensor.
  6. The target reaches tensor.to_dense() before later rank, hidden-size, and dtype checks.

weights_only=True constrains deserialization types; it does not compensate for a sparse invariant check that another request has disabled.

The complete stock actor-to-sink chain, traced in the affected source, is:

POST /v1/chat/completions (vllm/entrypoints/openai/chat_completion/api_router.py:41-61) -> OpenAIServingChat.create_chat_completion -> _create_chat_completion -> render_chat_request (vllm/entrypoints/openai/chat_completion/serving.py:206-280) -> OnlineRenderer.render_chat (vllm/renderers/online_renderer.py:95-190) -> preprocess_chat (vllm/renderers/online_renderer.py:335-380) -> BaseRenderer.render_chat_async (vllm/renderers/base.py:1070-1105) -> HfRenderer.render_messages_async (vllm/renderers/hf.py:1049-1085) -> parse_chat_messages_async (vllm/entrypoints/chat_utils.py:1911-1945) -> content-part parse_prompt_embeds and _load_prompt_embeds_async (vllm/entrypoints/chat_utils.py:1099-1120) -> AsyncMultiModalItemTracker.resolve_items (vllm/entrypoints/chat_utils.py:818-835) -> asyncio.gather of both prompt parts -> safe_load_prompt_embeds_async -> make_async -> loop.run_in_executor(executor=None, ...) (vllm/utils/async_utils.py:28-45) -> guarded torch.load -> to_dense().

The prompt async helper is created without an explicit executor, so it uses the event loop's default executor. This path is separate from the renderer's configurable pool. The deterministic scheduler run observed the two parts on distinct default-executor threads while leaving renderer_num_workers at its default of one.

prompt_embeds bypasses multimodal processing, and the tracker explicitly permits it when is_multimodal_model=False (vllm/entrypoints/chat_utils.py:793-837). Consequently, the primary trigger needs neither a multimodal model nor enable_mm_embeds.

The source also states that async wrappers must be thread-safe (vllm/utils/async_utils.py:28-38), while a target test acknowledges that the sparse flag is not thread-local and concurrent users can leak state (tests/renderers/test_sparse_tensor_validation.py:58-61).

Exploitability Analysis

The following evidence labels separate what was demonstrated from what remains conditional:

Severity

Not rated by the source.

Dates

Published
2026-09-10 09:45 UTC
Modified
2026-09-10 12:15 UTC

Affected packages and fixes

vllm

PyPI · All systems

Affected

  • introduced 0.21.0, fixed 0.26.0 (ecosystem)

Fixed versions

0.26.0

Fix

  • Fixed version 0.26.0
    pip install --upgrade vllm==0.26.0

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: PyPA Advisory Database · CC BY 4.0

Sources & licences