{"items":[{"id":"NVI-00016449","kind":"vulnerability","title":"vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds","revision":1,"unknowns":["Customer inventory, deployment, reachability and exploitation have not been inspected."],"lifecycle":"active","identifiers":["GHSA-8737-qx52-hjff","CVE-2026-71486"],"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-71b7e07318f2fb7b44fd93e95ee16802"],"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":"2026-09-04T21:32:09.000Z","value":"4.3 medium","meaning":"GitHub source severity; exploitability and local consequence require separate evidence.","source_id":"sr-71b7e07318f2fb7b44fd93e95ee16802"}],"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-71b7e07318f2fb7b44fd93e95ee16802","url":"https://github.com/advisories/GHSA-8737-qx52-hjff","basis":"vendor_advisory","notes":"GitHub Advisory Database; CC-BY-4.0. Each advisory links its original attribution. Null normalizes fields.","title":"GHSA-8737-qx52-hjff","publisher":"GitHub Advisory Database","observed_at":"2026-11-02T02:20:52.377Z"}],"affected_context":[{"certainty":"source_listed","source_ids":["sr-71b7e07318f2fb7b44fd93e95ee16802"],"technology":"vllm","known_exclusions":[],"conditions_summary":"## Summary\n\nThe `/v1/completions/derender` and `/v1/chat/completions/derender` endpoints accept caller-supplied `GenerateResponse` objects and postprocess every nested `choices[*].token_ids` list directly. Unlike the normal render/generate path, derender does not enforce model context length, resolved `max_tokens`, `max_num_seqs`, choice-count, or response-size bounds before detokenizing and returning the supplied token IDs. An authenticated API client can therefore make the CPU-only render frontend, or any server exposing these `/v1` derender routes, spend CPU and memory proportional to attacker-chosen generated-output-shaped JSON rather than to a bounded generation result.\n\n## Technical Details\n\nThe render router registers `/v1/chat/completions/derender` and `/v1/completions/derender` in `vllm/entrypoints/serve/render/api_router.py`, and the OpenAI API server attaches this router whenever `\"generate\"` or `\"render\"` is in `supported_tasks` (`vllm/entrypoints/openai/api_server.py`). The routes are under `/v1`, so they are part of the OpenAI-compatible HTTP API surface and are protected by the API-key middleware when `--api-key` is configured.\n\nThe request types trust generated-outp","public_affected_ranges":["< 0.26.0"]}],"null_published_at":"2026-11-04T10:04:27.945Z","source_updated_at":"2026-09-04T21:32:09.000Z","source_disclosed_at":"2026-09-04T21:32:07.000Z","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":"2026-11-02T02:20:52.377Z"}],"next_cursor":null,"snapshot_revision":"42594"}