{"items":[{"id":"NVI-00011754","kind":"vulnerability","title":"vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-58v5-2m8f-94pr","CVE-2026-105760"],"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-0aeb4dabf95e331adcd944829b8fc7a0"],"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":"2026-10-05T23:42:55.000Z","value":"5.3 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-1a147800185241d9ab645ba09a43de00"},{"kind":"EPSS","as_of":"2026-11-03T12:00:27.000Z","value":"0.297%","meaning":"FIRST EPSS model v2026.06.15; exploitation probability over 30 days, percentile 0.2243. Missing scores are unknown.","source_id":"sr-0aeb4dabf95e331adcd944829b8fc7a0"}],"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-1a147800185241d9ab645ba09a43de00","url":"https://github.com/advisories/GHSA-58v5-2m8f-94pr","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-58v5-2m8f-94pr","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:59:16.959Z"},{"id":"sr-0aeb4dabf95e331adcd944829b8fc7a0","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-2026-105760","publisher":"FIRST EPSS","observed_at":"2026-11-03T17:44:07.770Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-1a147800185241d9ab645ba09a43de00"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nThe OpenAI-compatible chat endpoint accepts request-level video loader options through `media_io_kwargs`. A caller can select the GLMGA sampler and provide large `fps` and `max_frames` values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the supplied video contains only a few frames. This work occurs in the shared media-loading executor before frame reads, allowing a tiny valid video and compact JSON options to consume disproportionate CPU time and memory and delay unrelated media requests.\n\nThe demonstrated impact is partial denial of service. No memory corruption, data disclosure, or code execution is claimed.\n\n## Affected configuration\n\nThe server must expose chat completions for a video-capable model and accept request-level `media_io_kwargs`. The model does not need to use GLMGA by default because the request value overrides the model's loader mapping. The proof of concept uses an inline two-frame video and explicitly selects the OpenCV decoder, so no external media host or GPU decoder is required.\n\nThe request is reachable without vLLM credentials when no API key is configured. With API-key authentication enabled, ","public_affected_ranges":[">= 0.23.0rc2, < 0.30.0"]}],"null_published_at":"2026-11-04T10:04:41.582Z","source_updated_at":"2026-10-05T23:42:55.000Z","source_disclosed_at":"2026-10-05T23:42:55.000Z","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":"2026-11-01T00:59:16.959Z"},{"id":"NVI-00011754","kind":"vulnerability","title":"vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-58v5-2m8f-94pr","CVE-2026-105760"],"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-1a147800185241d9ab645ba09a43de00"],"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":"2026-10-05T23:42:55.000Z","value":"5.3 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-1a147800185241d9ab645ba09a43de00"}],"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-1a147800185241d9ab645ba09a43de00","url":"https://github.com/advisories/GHSA-58v5-2m8f-94pr","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-58v5-2m8f-94pr","publisher":"GitHub Advisory Database","observed_at":"2026-11-01T00:59:16.959Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-1a147800185241d9ab645ba09a43de00"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nThe OpenAI-compatible chat endpoint accepts request-level video loader options through `media_io_kwargs`. A caller can select the GLMGA sampler and provide large `fps` and `max_frames` values. GLMGA first constructs an attacker-sized Python index list and then deduplicates it, even when the supplied video contains only a few frames. This work occurs in the shared media-loading executor before frame reads, allowing a tiny valid video and compact JSON options to consume disproportionate CPU time and memory and delay unrelated media requests.\n\nThe demonstrated impact is partial denial of service. No memory corruption, data disclosure, or code execution is claimed.\n\n## Affected configuration\n\nThe server must expose chat completions for a video-capable model and accept request-level `media_io_kwargs`. The model does not need to use GLMGA by default because the request value overrides the model's loader mapping. The proof of concept uses an inline two-frame video and explicitly selects the OpenCV decoder, so no external media host or GPU decoder is required.\n\nThe request is reachable without vLLM credentials when no API key is configured. With API-key authentication enabled, ","public_affected_ranges":[">= 0.23.0rc2, < 0.30.0"]}],"null_published_at":"2026-11-01T01:03:56.600Z","source_updated_at":"2026-10-05T23:42:55.000Z","source_disclosed_at":"2026-10-05T23:42:55.000Z","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":"2026-11-01T00:59:16.959Z"}],"next_cursor":null,"snapshot_revision":"42594"}