{"apiVersion":"1.0","identifier":"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.","publishedAt":"2026-08-25T19:16:54","lastModifiedAt":"2026-08-26T16:45:12","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-78379","cvssScore":8.1,"cvssVector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","epssProbability":0.0032,"riskScore":0.83,"affectedProduct":"Amazon Strands Agents Tools","affectedVersions":"<0.8.5","vulnerabilityType":"Library","operatingSystems":[],"links":{"self":"https://www.redsauce.net/api/cves/CVE-2026-78379","webPages":{"es":"https://www.redsauce.net/es/cves/CVE-2026-78379","en":"https://www.redsauce.net/en/cves/CVE-2026-78379","fr":"https://www.redsauce.net/fr/cves/CVE-2026-78379","pt":"https://www.redsauce.net/pt/cves/CVE-2026-78379","de":"https://www.redsauce.net/de/cves/CVE-2026-78379","sk":"https://www.redsauce.net/sk/cves/CVE-2026-78379","el":"https://www.redsauce.net/el/cves/CVE-2026-78379"},"source":"https://nvd.nist.gov/vuln/detail/CVE-2026-78379"}}