{"id":"CVE-2026-73556","aliases":["EUVD-2026-58063","GHSA-48jh-3gj7-fg8v","PYSEC-2026-3933"],"status":"published","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of CVE-2026-55574","description":"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.","severity":{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00515,"percentile":0.44354,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-1333","CWE-400"],"published":"2026-08-13T14:56:52Z","modified":"2026-11-04T02:47:50Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.26.0"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.26.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.26.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.24.0","0.25.0","0.25.1","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.26.0"}]}],"versions":["0.0.1","0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.10.1.1","0.10.2","0.11.0","0.11.1","0.11.2","0.12.0","0.13.0","0.14.0","0.14.1","0.15.0","0.15.1","0.16.0","0.17.0","0.17.1","0.18.0","0.18.1","0.19.0","0.19.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.20.0","0.20.1","0.20.2","0.21.0","0.22.0","0.22.1","0.23.0","0.24.0","0.25.0","0.25.1","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v","tags":["x_refsource_CONFIRM","exploit","Vendor Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/pull/47595","tags":["x_refsource_MISC","Issue Tracking","Patch","fix","web"]},{"url":"https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://github.com/vllm-project/vllm/releases/tag/v0.26.0","tags":["x_refsource_MISC","Release Notes","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-73556","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-48jh-3gj7-fg8v","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/73xxx/CVE-2026-73556.json","tags":["advisory"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]},{"url":"https://pypi.org/project/vllm","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-73556","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of CVE-2026-55574","description":"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.","status":"published","published":"2026-08-13T14:56:52.569Z","modified":"2026-08-14T16:52:40.458Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium","assessor":"cna"}],"cwes":["CWE-400","CWE-1333"],"updated_at":"2026-11-02T13:43:22.599321Z"}],"euvd":[{"id":"EUVD-2026-58063","description":"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.","status":"published","published":"2026-08-13T14:56:52Z","modified":"2026-08-14T16:52:40Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium"}],"updated_at":"2026-11-02T18:01:53.90055Z"}],"ghsa":[{"id":"GHSA-48jh-3gj7-fg8v","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m","description":"### Summary\n\nThe fix for `GHSA-rwxx-mrjm-wc2m` (\"ReDoS via `structured_outputs.regex` compiled without timeout\") wrapped the regex compile in the **xgrammar** and **outlines** backends with `compile_regex_with_timeout` (and, for outlines, `validate_regex_is_buildable`). The **lm-format-enforcer** backend was left unguarded: it compiles the attacker-supplied regex with no timeout and no buildability check. A single request with a catastrophic regex hangs the structured-output compile step and stalls the engine worker (denial of service).\n\n### Affected code (HEAD d6d39c1)\n\n`vllm/v1/structured_output/backend_lm_format_enforcer.py`:\n- line 110: `character_level_parser = lmformatenforcer.RegexParser(grammar_spec)` — builds an `interegular` FSM from the attacker regex synchronously, **no timeout**.\n- line 155: `validate_structured_output_request_lm_format_enforcer` returns immediately on `if so_params.regex:` — **no validation**.\n\nSibling backends that WERE patched by GHSA-rwxx:\n- `backend_xgrammar.py:92` → `compile_regex_with_timeout(...)`.\n- `backend_outlines.py:65` → `compile_regex_with_timeout(...)` (plus `validate_regex_is_buildable`).\n\nlm-format-enforcer uses the same `interegular` DFA-construction primitive the advisory cites for the outlines backend.\n\n### Reproduction (runtime-verified against the sink)\n\nThe sink `lmformatenforcer.RegexParser(\u003cregex\u003e)` was exercised directly (this is exactly what the backend calls):\n\n```\nbaseline  '[0-9]{3}'          -\u003e 0.0002 s\nattacker  '(a{1,300}){300}'   -\u003e DID NOT COMPLETE in 20 s (one core pegged at 100% in interegular FSM construction)\n```\n\nEnd-to-end: start `vllm serve \u003cmodel\u003e --structured-outputs-config '{\"backend\":\"lm-format-enforcer\"}'`, then `POST /v1/completions` with `{\"structured_outputs\":{\"regex\":\"(a{1,300}){300}\"}, ...}`. The request never returns; because grammar compile runs in the engine's structured-output path, concurrent requests stall = worker-level DoS. The identical request against the outlines backend is bounded by `compile_regex_with_timeout` and returns a clean error.\n\n### Impact\n\nUnauthenticated denial of service (vLLM ships with no authentication by default). One request pegs a CPU core and blocks the structured-output engine path.\n\n**Reachability precondition:** the operator must have selected `backend=lm-format-enforcer` via `--structured-outputs-config` (the default is `auto` → xgrammar). This is the same opt-in tier as the outlines backend that GHSA-rwxx already covered.\n\n### Suggested remediation\n\nRoute the lm-format-enforcer regex compile (`backend_lm_format_enforcer.py:110`) through the same `compile_regex_with_timeout` guard already applied to the xgrammar and outlines backends, and reject un-buildable / oversized patterns in `validate_structured_output_request_lm_format_enforcer`.","status":"published","published":"2026-09-04T21:37:00Z","modified":"2026-09-04T21:37:01Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium"}],"cwes":["CWE-400","CWE-1333"],"updated_at":"2026-11-02T14:41:13.477974Z"}],"nvd":[{"id":"CVE-2026-73556","description":"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.","status":"published","published":"2026-08-13T15:20:17.927Z","modified":"2026-09-28T18:42:04.937Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium","assessor":"secondary"}],"cwes":["CWE-400","CWE-1333"],"updated_at":"2026-11-02T14:12:37.557758Z"}],"osv":[{"id":"CVE-2026-73556","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of CVE-2026-55574","description":"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.","status":"published","published":"2026-08-13T14:56:52.569Z","modified":"2026-11-10T02:32:39.31852891Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium"}],"cwes":["CWE-1333","CWE-400"],"updated_at":"2026-11-10T02:45:42.584685Z"},{"id":"GHSA-48jh-3gj7-fg8v","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m","description":"### Summary\n\nThe fix for `GHSA-rwxx-mrjm-wc2m` (\"ReDoS via `structured_outputs.regex` compiled without timeout\") wrapped the regex compile in the **xgrammar** and **outlines** backends with `compile_regex_with_timeout` (and, for outlines, `validate_regex_is_buildable`). The **lm-format-enforcer** backend was left unguarded: it compiles the attacker-supplied regex with no timeout and no buildability check. A single request with a catastrophic regex hangs the structured-output compile step and stalls the engine worker (denial of service).\n\n### Affected code (HEAD d6d39c1)\n\n`vllm/v1/structured_output/backend_lm_format_enforcer.py`:\n- line 110: `character_level_parser = lmformatenforcer.RegexParser(grammar_spec)` — builds an `interegular` FSM from the attacker regex synchronously, **no timeout**.\n- line 155: `validate_structured_output_request_lm_format_enforcer` returns immediately on `if so_params.regex:` — **no validation**.\n\nSibling backends that WERE patched by GHSA-rwxx:\n- `backend_xgrammar.py:92` → `compile_regex_with_timeout(...)`.\n- `backend_outlines.py:65` → `compile_regex_with_timeout(...)` (plus `validate_regex_is_buildable`).\n\nlm-format-enforcer uses the same `interegular` DFA-construction primitive the advisory cites for the outlines backend.\n\n### Reproduction (runtime-verified against the sink)\n\nThe sink `lmformatenforcer.RegexParser(\u003cregex\u003e)` was exercised directly (this is exactly what the backend calls):\n\n```\nbaseline  '[0-9]{3}'          -\u003e 0.0002 s\nattacker  '(a{1,300}){300}'   -\u003e DID NOT COMPLETE in 20 s (one core pegged at 100% in interegular FSM construction)\n```\n\nEnd-to-end: start `vllm serve \u003cmodel\u003e --structured-outputs-config '{\"backend\":\"lm-format-enforcer\"}'`, then `POST /v1/completions` with `{\"structured_outputs\":{\"regex\":\"(a{1,300}){300}\"}, ...}`. The request never returns; because grammar compile runs in the engine's structured-output path, concurrent requests stall = worker-level DoS. The identical request against the outlines backend is bounded by `compile_regex_with_timeout` and returns a clean error.\n\n### Impact\n\nUnauthenticated denial of service (vLLM ships with no authentication by default). One request pegs a CPU core and blocks the structured-output engine path.\n\n**Reachability precondition:** the operator must have selected `backend=lm-format-enforcer` via `--structured-outputs-config` (the default is `auto` → xgrammar). This is the same opt-in tier as the outlines backend that GHSA-rwxx already covered.\n\n### Suggested remediation\n\nRoute the lm-format-enforcer regex compile (`backend_lm_format_enforcer.py:110`) through the same `compile_regex_with_timeout` guard already applied to the xgrammar and outlines backends, and reject un-buildable / oversized patterns in `validate_structured_output_request_lm_format_enforcer`.","status":"published","published":"2026-09-04T21:37:00Z","modified":"2026-09-10T12:25:34.716905199Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium"}],"cwes":["CWE-1333","CWE-400"],"updated_at":"2026-11-02T15:46:36.782754Z"},{"id":"PYSEC-2026-3933","title":"vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m","description":"### Summary\n\nThe fix for `GHSA-rwxx-mrjm-wc2m` (\"ReDoS via `structured_outputs.regex` compiled without timeout\") wrapped the regex compile in the **xgrammar** and **outlines** backends with `compile_regex_with_timeout` (and, for outlines, `validate_regex_is_buildable`). The **lm-format-enforcer** backend was left unguarded: it compiles the attacker-supplied regex with no timeout and no buildability check. A single request with a catastrophic regex hangs the structured-output compile step and stalls the engine worker (denial of service).\n\n### Affected code (HEAD d6d39c1)\n\n`vllm/v1/structured_output/backend_lm_format_enforcer.py`:\n- line 110: `character_level_parser = lmformatenforcer.RegexParser(grammar_spec)` — builds an `interegular` FSM from the attacker regex synchronously, **no timeout**.\n- line 155: `validate_structured_output_request_lm_format_enforcer` returns immediately on `if so_params.regex:` — **no validation**.\n\nSibling backends that WERE patched by GHSA-rwxx:\n- `backend_xgrammar.py:92` → `compile_regex_with_timeout(...)`.\n- `backend_outlines.py:65` → `compile_regex_with_timeout(...)` (plus `validate_regex_is_buildable`).\n\nlm-format-enforcer uses the same `interegular` DFA-construction primitive the advisory cites for the outlines backend.\n\n### Reproduction (runtime-verified against the sink)\n\nThe sink `lmformatenforcer.RegexParser(\u003cregex\u003e)` was exercised directly (this is exactly what the backend calls):\n\n```\nbaseline  '[0-9]{3}'          -\u003e 0.0002 s\nattacker  '(a{1,300}){300}'   -\u003e DID NOT COMPLETE in 20 s (one core pegged at 100% in interegular FSM construction)\n```\n\nEnd-to-end: start `vllm serve \u003cmodel\u003e --structured-outputs-config '{\"backend\":\"lm-format-enforcer\"}'`, then `POST /v1/completions` with `{\"structured_outputs\":{\"regex\":\"(a{1,300}){300}\"}, ...}`. The request never returns; because grammar compile runs in the engine's structured-output path, concurrent requests stall = worker-level DoS. The identical request against the outlines backend is bounded by `compile_regex_with_timeout` and returns a clean error.\n\n### Impact\n\nUnauthenticated denial of service (vLLM ships with no authentication by default). One request pegs a CPU core and blocks the structured-output engine path.\n\n**Reachability precondition:** the operator must have selected `backend=lm-format-enforcer` via `--structured-outputs-config` (the default is `auto` → xgrammar). This is the same opt-in tier as the outlines backend that GHSA-rwxx already covered.\n\n### Suggested remediation\n\nRoute the lm-format-enforcer regex compile (`backend_lm_format_enforcer.py:110`) through the same `compile_regex_with_timeout` guard already applied to the xgrammar and outlines backends, and reject un-buildable / oversized patterns in `validate_structured_output_request_lm_format_enforcer`.","status":"published","published":"2026-09-10T09:45:00.190897Z","modified":"2026-09-10T12:15:13.663911452Z","cvss":[{"version":"3.1","score":5.3,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L","level":"medium"}],"updated_at":"2026-11-02T15:52:57.255153Z"}]}}