{"items":[{"id":"NVI-00010686","kind":"vulnerability","title":"vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-gx7p-2j49-hfq4","CVE-2026-114055"],"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-b280df4f00fa703d7ace3644a779348b"],"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":"CVSS","as_of":"2026-10-23T20:58:38.000Z","value":"7.5 high","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-a455fdf8b510160b98104a3295ac7966"},{"kind":"EPSS","as_of":"2026-10-31T12:00:27.000Z","value":"0.420%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.36331. Missing scores are unknown.","source_id":"sr-b280df4f00fa703d7ace3644a779348b"}],"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-a455fdf8b510160b98104a3295ac7966","url":"https://github.com/advisories/GHSA-gx7p-2j49-hfq4","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-gx7p-2j49-hfq4","publisher":"GitHub Advisory Database","observed_at":"2026-10-31T22:07:08.657Z"},{"id":"sr-b280df4f00fa703d7ace3644a779348b","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-2026-114055","publisher":"FIRST EPSS","observed_at":"2026-10-31T23:13:27.688Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-a455fdf8b510160b98104a3295ac7966"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nAPI clients can supply arbitrary `mm_processor_kwargs` per request. vLLM\nforwards these values through the multimodal rendering and processing pipeline\nto Hugging Face and custom image/video processor constructors and calls.\nResource-sensitive values such as image size, patch size, patch count, crop\ncount, or frame count can therefore be controlled by a remote client.\n\nFor processors that upscale inputs, a single request can force an allocation\nlarge enough to terminate the API server or worker with an out-of-memory\ncondition.\n\n## Affected Components\n\nThe per-request field was introduced in commit\n`041e29471671a3d43afedb6a749421d56ef4d3e7` and first shipped in v0.7.3.\nThe generic forwarding path remains present in current `main`.\n\nThe Isaac path is a concrete high-amplification example:\n\n- `ChatCompletionRequest.mm_processor_kwargs`\n- `OnlineRenderer` request extras\n- `MMProcessorInputs.hf_processor_mm_kwargs`\n- `BaseMultiModalProcessor.info.get_hf_processor(**hf_processor_mm_kwargs)`\n- `IsaacProcessingInfo.get_image_processor(**kwargs)`\n- `IsaacImageProcessor(**kwargs)`\n- `process_vision_for_patches()`\n\nEquivalent constructor forwarding exists in InternVL-derived proce","public_affected_ranges":[">= 0.7.3, < 0.31.0"]}],"null_published_at":"2026-11-08T08:10:32.017Z","source_updated_at":"2026-10-23T20:58:38.000Z","source_disclosed_at":"2026-10-23T20:58:36.000Z","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":"2026-10-31T22:07:08.657Z"},{"id":"NVI-00010686","kind":"vulnerability","title":"vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-gx7p-2j49-hfq4","CVE-2026-114055"],"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-a455fdf8b510160b98104a3295ac7966"],"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":"CVSS","as_of":"2026-10-23T20:58:38.000Z","value":"7.5 high","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-a455fdf8b510160b98104a3295ac7966"}],"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-a455fdf8b510160b98104a3295ac7966","url":"https://github.com/advisories/GHSA-gx7p-2j49-hfq4","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-gx7p-2j49-hfq4","publisher":"GitHub Advisory Database","observed_at":"2026-10-31T22:07:08.657Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-a455fdf8b510160b98104a3295ac7966"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nAPI clients can supply arbitrary `mm_processor_kwargs` per request. vLLM\nforwards these values through the multimodal rendering and processing pipeline\nto Hugging Face and custom image/video processor constructors and calls.\nResource-sensitive values such as image size, patch size, patch count, crop\ncount, or frame count can therefore be controlled by a remote client.\n\nFor processors that upscale inputs, a single request can force an allocation\nlarge enough to terminate the API server or worker with an out-of-memory\ncondition.\n\n## Affected Components\n\nThe per-request field was introduced in commit\n`041e29471671a3d43afedb6a749421d56ef4d3e7` and first shipped in v0.7.3.\nThe generic forwarding path remains present in current `main`.\n\nThe Isaac path is a concrete high-amplification example:\n\n- `ChatCompletionRequest.mm_processor_kwargs`\n- `OnlineRenderer` request extras\n- `MMProcessorInputs.hf_processor_mm_kwargs`\n- `BaseMultiModalProcessor.info.get_hf_processor(**hf_processor_mm_kwargs)`\n- `IsaacProcessingInfo.get_image_processor(**kwargs)`\n- `IsaacImageProcessor(**kwargs)`\n- `process_vision_for_patches()`\n\nEquivalent constructor forwarding exists in InternVL-derived proce","public_affected_ranges":[">= 0.7.3, < 0.31.0"]}],"null_published_at":"2026-10-31T22:27:09.628Z","source_updated_at":"2026-10-23T20:58:38.000Z","source_disclosed_at":"2026-10-23T20:58:36.000Z","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":"2026-10-31T22:07:08.657Z"}],"next_cursor":null,"snapshot_revision":"42594"}