{"items":[{"id":"NVI-00016326","kind":"vulnerability","title":"vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing","revision":2,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected.","NVD lastModified does not establish freshness of every associated CPE record."],"lifecycle":"active","identifiers":["GHSA-pq5c-rjhq-qp7p","CVE-2026-34755"],"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-0f6e3e8dda8fef1e40d434d941667e29"],"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":"2026-08-25T15:33:11.000Z","value":"6.5 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-6849aa79f27248436244cd113b471f67"},{"kind":"CVSS","as_of":"2026-08-25T13:18:39.240Z","value":"6.5 MEDIUM (3.1)","meaning":"security-advisories@github.com severity; no combined Null risk score.","source_id":"sr-0f6e3e8dda8fef1e40d434d941667e29"},{"kind":"CVSS","as_of":"2026-08-25T13:18:39.240Z","value":"6.5 MEDIUM (3.1)","meaning":"0b0ca135-0b70-47e7-9f44-1890c2a1c46c severity; no combined Null risk score.","source_id":"sr-0f6e3e8dda8fef1e40d434d941667e29"}],"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-6849aa79f27248436244cd113b471f67","url":"https://github.com/advisories/GHSA-pq5c-rjhq-qp7p","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-pq5c-rjhq-qp7p","publisher":"GitHub Advisory Database","observed_at":"2026-11-02T09:56:37.775Z"},{"id":"sr-0f6e3e8dda8fef1e40d434d941667e29","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-34755","basis":"official_catalog","notes":"This product uses data from the NVD API but is not endorsed or certified by the NVD.","title":"CVE-2026-34755","publisher":"NIST National Vulnerability Database","observed_at":"2026-11-07T13:58:13.921Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-6849aa79f27248436244cd113b471f67"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nThe `VideoMediaIO.load_base64()` method at `vllm/multimodal/media/video.py:51-62` splits `video/jpeg` data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The `num_frames` parameter (default: 32), which is enforced by the `load_bytes()` code path at line 47-48, is completely bypassed in the `video/jpeg` base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM.\n\n## Details\n\n### Vulnerable code\n\n```python\n# video.py:51-62\ndef load_base64(self, media_type: str, data: str) -> tuple[npt.NDArray, dict[str, Any]]:\n    if media_type.lower() == \"video/jpeg\":\n        load_frame = partial(self.image_io.load_base64, \"image/jpeg\")\n        return np.stack(\n            [np.asarray(load_frame(frame_data)) for frame_data in data.split(\",\")]\n            #                                                       ^^^^^^^^^^\n            # Unbounded split — no frame count limit\n        ), {}\n    return self.load_bytes(base64.b64decode(data))\n```\n\nThe `load_bytes()` path (line 47-48) properly delegates to a video loade","public_affected_ranges":[">= 0.7.0, < 0.19.0"]}],"null_published_at":"2026-11-07T18:43:12.064Z","source_updated_at":"2026-08-25T15:33:11.000Z","source_disclosed_at":"2026-04-03T21:51:35.000Z","is_synthetic_fixture":false,"null_last_reviewed_at":null,"public_change_summary":"Source facts changed; compare the preserved prior revision.","null_first_observed_at":"2026-11-02T09:56:37.775Z"},{"id":"NVI-00016326","kind":"vulnerability","title":"vLLM: Denial of Service via Unbounded Frame Count in video/jpeg Base64 Processing","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-pq5c-rjhq-qp7p","CVE-2026-34755"],"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-6849aa79f27248436244cd113b471f67"],"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":"2026-08-25T15:33:11.000Z","value":"6.5 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-6849aa79f27248436244cd113b471f67"}],"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-6849aa79f27248436244cd113b471f67","url":"https://github.com/advisories/GHSA-pq5c-rjhq-qp7p","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-pq5c-rjhq-qp7p","publisher":"GitHub Advisory Database","observed_at":"2026-11-02T09:56:37.775Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-6849aa79f27248436244cd113b471f67"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nThe `VideoMediaIO.load_base64()` method at `vllm/multimodal/media/video.py:51-62` splits `video/jpeg` data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The `num_frames` parameter (default: 32), which is enforced by the `load_bytes()` code path at line 47-48, is completely bypassed in the `video/jpeg` base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM.\n\n## Details\n\n### Vulnerable code\n\n```python\n# video.py:51-62\ndef load_base64(self, media_type: str, data: str) -> tuple[npt.NDArray, dict[str, Any]]:\n    if media_type.lower() == \"video/jpeg\":\n        load_frame = partial(self.image_io.load_base64, \"image/jpeg\")\n        return np.stack(\n            [np.asarray(load_frame(frame_data)) for frame_data in data.split(\",\")]\n            #                                                       ^^^^^^^^^^\n            # Unbounded split — no frame count limit\n        ), {}\n    return self.load_bytes(base64.b64decode(data))\n```\n\nThe `load_bytes()` path (line 47-48) properly delegates to a video loade","public_affected_ranges":[">= 0.7.0, < 0.19.0"]}],"null_published_at":"2026-11-04T10:04:27.932Z","source_updated_at":"2026-08-25T15:33:11.000Z","source_disclosed_at":"2026-04-03T21:51:35.000Z","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":"2026-11-02T09:56:37.775Z"}],"next_cursor":null,"snapshot_revision":"42594"}