{"items":[{"id":"NVI-00016203","kind":"vulnerability","title":"vLLM denial of service via prompt embeds on M-RoPE models","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-33cg-gxv8-3p8g","CVE-2026-55514"],"plain_summary":"GitHub lists this reviewed advisory for vllm. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-1765027cfd9017abffc6d54ff76101b4"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[{"kind":"EPSS","as_of":"2026-11-04T12:03:12.000Z","value":"0.665%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.51899. Missing scores are unknown.","source_id":"sr-1765027cfd9017abffc6d54ff76101b4"}],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-44745e02e1b0e6d731e8e72d50d92cd3","url":"https://github.com/advisories/GHSA-33cg-gxv8-3p8g","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-33cg-gxv8-3p8g","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T02:49:06.528Z"},{"id":"sr-1765027cfd9017abffc6d54ff76101b4","url":"https://www.first.org/epss/data.html","basis":"official_catalog","notes":"FIRST EPSS; probability of exploitation in the next 30 days, not local compromise. Dataset date/model retained; FIRST services terms apply.","title":"CVE-2026-55514","publisher":"FIRST EPSS","observed_at":"2026-11-04T17:58:50.332Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-44745e02e1b0e6d731e8e72d50d92cd3"],"technology":"vllm","known_exclusions":[],"conditions_summary":"### Summary\n_Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server._\n\nSending a pure prompt embeds payload in a `/v1/completions` request with a model using M-RoPE causes the EngineCore to fail an assertion and fatally crash, shutting down the entire server application.\n\nAny remote user who is authorized to make a `/v1/completions` endpoint can trivially make such a request and induce a crash.\n\n### Details\n_Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer._\n\nIn commit 56669c1, a simple assert intended to be a type-narrowing assert was added to the `_init_mrope_positions` method in `GPUModelRunner` (the offending line on main at the time of writing: https://github.com/vllm-project/vllm/blob/2d481f8a946ee0521872af0f098674a8ee01ce4a/vllm/v1/worker/gpu_model_runner.py#L1588-L1607).\n\n```python\nassert req_state.prompt_token_ids is not None, (\n            \"M-RoPE requires prompt_token_ids","public_affected_ranges":[">= 0.12.0, < 0.24.0"]}],"null_published_at":"2026-11-08T19:53:38.937Z","source_updated_at":"2026-07-20T19:13:08.000Z","source_disclosed_at":"2026-07-20T19:13:07.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Dated EPSS estimate updated; this is not a new disclosure or proof of exploitation.","null_first_observed_at":"2026-11-04T02:49:06.528Z"},{"id":"NVI-00016203","kind":"vulnerability","title":"vLLM denial of service via prompt embeds on M-RoPE models","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-33cg-gxv8-3p8g","CVE-2026-55514"],"plain_summary":"GitHub lists this reviewed advisory for vllm. Published version ranges and source prerequisites are shown below; this is not an inspection of a visitor’s application.","review_status":"source_listed","control_topics":[],"public_actions":[{"summary":"Identify the exact component and deployed version, examine the linked publisher’s conditions, and retain evidence of any mitigation.","source_ids":["sr-44745e02e1b0e6d731e8e72d50d92cd3"],"action_type":"investigate","limitations":"Confirm current vendor support, compatibility and deployment evidence. This report has not tested a fix in your system.","current_supported_target":null}],"schema_version":"1.1.0","source_metrics":[],"why_it_matters":"Published affected context helps an owner decide what evidence to gather. This report has not examined your application.","related_sources":[{"id":"sr-44745e02e1b0e6d731e8e72d50d92cd3","url":"https://github.com/advisories/GHSA-33cg-gxv8-3p8g","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-33cg-gxv8-3p8g","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T02:49:06.528Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-44745e02e1b0e6d731e8e72d50d92cd3"],"technology":"vllm","known_exclusions":[],"conditions_summary":"### Summary\n_Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server._\n\nSending a pure prompt embeds payload in a `/v1/completions` request with a model using M-RoPE causes the EngineCore to fail an assertion and fatally crash, shutting down the entire server application.\n\nAny remote user who is authorized to make a `/v1/completions` endpoint can trivially make such a request and induce a crash.\n\n### Details\n_Give all details on the vulnerability. Pointing to the incriminated source code is very helpful for the maintainer._\n\nIn commit 56669c1, a simple assert intended to be a type-narrowing assert was added to the `_init_mrope_positions` method in `GPUModelRunner` (the offending line on main at the time of writing: https://github.com/vllm-project/vllm/blob/2d481f8a946ee0521872af0f098674a8ee01ce4a/vllm/v1/worker/gpu_model_runner.py#L1588-L1607).\n\n```python\nassert req_state.prompt_token_ids is not None, (\n            \"M-RoPE requires prompt_token_ids","public_affected_ranges":[">= 0.12.0, < 0.24.0"]}],"null_published_at":"2026-11-04T10:04:27.918Z","source_updated_at":"2026-07-20T19:13:08.000Z","source_disclosed_at":"2026-07-20T19:13:07.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"First indexed by Null; source disclosure date is shown separately.","null_first_observed_at":"2026-11-04T02:49:06.528Z"}],"next_cursor":null,"snapshot_revision":"42594"}