{"items":[{"id":"NVI-00016067","kind":"vulnerability","title":"vLLM Vulnerable to Remote DoS via Special-Token Placeholders","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-hpv8-x276-m59f","CVE-2026-44222"],"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-14db952656f621a188ee8063137b89fb"],"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":"2026-07-17T16:21:20.000Z","value":"6.5 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-14db952656f621a188ee8063137b89fb"}],"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-14db952656f621a188ee8063137b89fb","url":"https://github.com/advisories/GHSA-hpv8-x276-m59f","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-hpv8-x276-m59f","publisher":"GitHub Advisory Database","observed_at":"2026-11-04T09:59:26.779Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-14db952656f621a188ee8063137b89fb"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\nThis report explains a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on `image_grid_thw`/`video_grid_thw` are affected. Severity: High (remote DoS). Reproduced on vLLM 0.10.0 with Qwen2.5-VL.\n\n## Details\n- Affected component: multimodal input position computation.\n- File/functions (paths are indicative):\n  - vllm/model_executor/layers/rotary_embedding.py\n    - get_input_positions_tensor(...)\n    - _vl_get_input_positions_tensor(...)\n- Failure mechanism:\n  - The code counts detected vision tokens and then indexes video_grid_thw/image_grid_thw accordingly.\n  - When user input carries placeholder tokens but no actual multimodal payload, these grids are empty. The code does not bounds-check before indexing.\n\nRepresentative snippet (context):\n```python\n# vllm/model_executor/layers/rotary_embedding.py\n@classmethod\ndef _vl_g","public_affected_ranges":[">= 0.6.1, < 0.20.0"]}],"null_published_at":"2026-11-04T10:04:27.875Z","source_updated_at":"2026-07-17T16:21:20.000Z","source_disclosed_at":"2026-05-05T22:21:41.000Z","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":"2026-11-04T09:59:26.779Z"}],"next_cursor":null,"snapshot_revision":"42594"}