{"id":"CVE-2026-78379","aliases":["EUVD-2026-65735"],"status":"published","title":"Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools","description":"Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.","severity":{"version":"4.0","score":9.2,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","level":"critical","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00671,"percentile":0.5247,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-1427"],"published":"2026-08-25T19:05:57Z","modified":"2026-08-26T16:45:12Z","products":[{"vendor":"amazon","product":"strands-agents-tools"}],"references":[{"url":"https://pypi.org/project/strands-agents-tools/0.8.5/","tags":["patch","release-notes"]},{"url":"https://aws.amazon.com/security/security-bulletins/2026-089-aws/","tags":["vendor-advisory"]}],"sources":{"cve":[{"id":"CVE-2026-78379","title":"Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools","description":"Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.","status":"published","published":"2026-08-25T19:05:57.779Z","modified":"2026-08-25T19:20:51.512Z","cvss":[{"version":"4.0","score":9.2,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","level":"critical","assessor":"cna"},{"version":"3.1","score":8.1,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-1427"],"updated_at":"2026-11-02T13:34:48.658051Z"}],"euvd":[{"id":"EUVD-2026-65735","description":"Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.","status":"published","published":"2026-08-25T19:05:57Z","modified":"2026-08-25T19:20:51Z","cvss":[{"version":"4.0","score":9.2,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N","level":"critical"}],"updated_at":"2026-11-02T18:01:32.174502Z"}],"nvd":[{"id":"CVE-2026-78379","description":"Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.","status":"published","published":"2026-08-25T19:16:54.467Z","modified":"2026-08-26T16:45:12.02Z","cvss":[{"version":"4.0","score":9.2,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"critical","assessor":"secondary"},{"version":"3.1","score":8.1,"vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"high","assessor":"secondary"}],"updated_at":"2026-11-02T14:12:41.347728Z"}]}}