{"id":"CVE-2025-30405","kind":"vulnerability","aliases":["CVE-2025-30405","GHSA-84m3-f99p-cqx5"],"related":[],"title":"ExecuTorch integer overflow vulnerability","description":"An integer overflow vulnerability in the loading of ExecuTorch models can cause objects to be placed outside their allocated memory area, potentially resulting in code execution or other undesirable effects. This issue affects ExecuTorch prior to commit 0830af8207240df8d7f35b984cdf8bc35d74fa73.","summary":"ExecuTorch is PyTorch's on-device inference runtime. A integer overflow when loading a model file can place objects outside their allocated memory, which can lead to code execution or other undesirable effects.","severity":"critical","cvss":9.8,"epss":0.00619,"exploited":false,"exploited_at":null,"products":[{"name":"executorch","fixed":["0.7.0"],"affected":"< 0.7.0","ecosystem":"pypi"},{"name":"org.pytorch:executorch-android","fixed":["0.7.0"],"affected":"< 0.7.0","ecosystem":"maven"},{"name":"github.com/pytorch/executorch","fixed":["0.7.0"],"affected":"< 0.7.0","ecosystem":"swift"}],"ecosystems":["maven","pypi","swift"],"tags":["android","cwe-190","executorch","on-device-ai","package","python","swift"],"not_affected_if":["not-using-executorch","trusted-model-files-only"],"how_to_check":"- Run `pip show executorch` and check whether the version is below `0.7.0`.\n- For Android, check whether the `org.pytorch:executorch-android` dependency is below `0.7.0`.\n- For Swift, check whether the `github.com/pytorch/executorch` package is below `0.7.0`.","fix":"- Upgrade `executorch` (PyPI) to `0.7.0` or later.\n- Upgrade `org.pytorch:executorch-android` (Maven) to `0.7.0` or later.\n- Upgrade `github.com/pytorch/executorch` (Swift) to `0.7.0` or later.","status":"open","published_at":"2025-08-07T23:15:26+00:00","first_seen_at":"2026-10-27T16:30:45+00:00","triaged_at":"2026-10-27T16:31:49+00:00","updated_at":"2026-10-27T16:33:07+00:00","category":"package","confidence":0.7,"triage":{"at":"2026-10-27T16:31:49Z","model":"claude-haiku-5-5","output":{"fix":"- Upgrade `executorch` (PyPI) to `0.7.0` or later.\n- Upgrade `org.pytorch:executorch-android` (Maven) to `0.7.0` or later.\n- Upgrade `github.com/pytorch/executorch` (Swift) to `0.7.0` or later.","reach":"unknown","title":"ExecuTorch: integer overflow in model loading lets a crafted model run code","impact":"high","summary":"ExecuTorch is PyTorch's on-device inference runtime. A integer overflow when loading a model file can place objects outside their allocated memory, which can lead to code execution or other undesirable effects.","category":"package","nicknames":[],"who_cares":["python","android","swift","executorch","on-device-ai"],"confidence":0.7,"needs_auth":"unknown","worst_case":"crafted model file could run code on the loading process","analyst_note":"","how_to_check":"- Run `pip show executorch` and check whether the version is below `0.7.0`.\n- For Android, check whether the `org.pytorch:executorch-android` dependency is below `0.7.0`.\n- For Swift, check whether the `github.com/pytorch/executorch` package is below `0.7.0`.","needs_analyst":false,"not_affected_if":["not-using-executorch","trusted-model-files-only"],"who_is_affected":"Teams that load ExecuTorch models in their application, whether on a server, a mobile app or an embedded device. Exposure depends on whether the model files come from an untrusted source, which the sources do not detail. Teams not using ExecuTorch can skip it.","user_interaction":"unknown","needs_special_setup":"unknown","severity_if_unknown":"critical"},"cost_usd":0.000638,"input_tokens":3429,"output_tokens":590,"severity_before":"critical"},"analyst_status":null,"analyst_note":null,"search":"'-190':26B '-2025':6A,14A '-30405':7A,15A '/pytorch/executorch':23A '0830af8207240df8d7f35b984cdf8bc35d74fa73':106C '84m3':10A 'affect':101C 'ai':31B 'alloc':57B,87C 'android':20A,24B 'area':89C 'caus':80C 'code':63B,93C 'commit':105C 'cqx5':12A 'cve':5A,13A 'cwe':25B 'devic':30B,41B 'effect':68B,98C 'execut':64B,94C 'executorch':1A,16A,19A,27B,35B,77C,102C 'executorch-android':18A 'f99p':11A 'file':51B 'ghsa':9A 'ghsa-84m3-f99p-cqx5':8A 'github.com':22A 'github.com/pytorch/executorch':21A 'infer':42B 'integ':2A,45B,70C 'issu':100C 'lead':61B 'load':48B,75C 'memori':58B,88C 'model':50B,78C 'object':54B,81C 'on-devic':39B 'on-device-ai':28B 'org.pytorch':17A 'outsid':55B,85C 'overflow':3A,46B,71C 'packag':32B 'place':53B,84C 'potenti':90C 'prior':103C 'python':33B 'pytorch':37B 'result':91C 'runtim':43B 'swift':34B 'undesir':67B,97C 'vulner':4A,72C","nicknames":[],"mitigations":[],"who_affected":"Teams that load ExecuTorch models in their application, whether on a server, a mobile app or an embedded device. Exposure depends on whether the model files come from an untrusted source, which the sources do not detail. Teams not using ExecuTorch can skip it.","tier":"B","verified":{},"analyst_revisit_at":null,"first_public_at":"2025-08-07T23:15:26+00:00","kev":null,"cvss_vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","cvss_by":"GitHub","poc_count":0,"sources":[{"source":"ghsa","external_id":"GHSA-84m3-f99p-cqx5","url":"https://github.com/advisories/GHSA-84m3-f99p-cqx5","severity":"critical","published_at":"2025-08-08T00:30:26+00:00","modified_at":"2026-10-27T16:28:01+00:00","first_seen_at":"2026-10-27T16:30:45+00:00","fetched_at":"2026-10-27T16:30:45+00:00","note":null},{"source":"nvd","external_id":"CVE-2025-30405","url":"https://nvd.nist.gov/vuln/detail/CVE-2025-30405","severity":null,"published_at":"2025-08-07T23:15:26+00:00","modified_at":"2026-06-17T09:08:39+00:00","first_seen_at":"2026-10-27T16:33:07+00:00","fetched_at":"2026-10-27T16:33:07+00:00","note":null}],"documents":[],"notice":"Free to read at a human pace. An API with keys and an MCP server are in preparation; early access: hello@infrastack.ai"}