{"id":"CVE-2026-45311","sourceIdentifier":"security-advisories@github.com","published":"2026-05-28T18:16:35.170","lastModified":"2026-10-26T13:10:00.140","vulnStatus":"Deferred","cveTags":[],"descriptions":[{"lang":"en","value":"CodeWhale is a DeepSeek + MiMo coding agent in terminal. From 0.3.0 to 0.8.23, the run_tests tool executes cargo test in the workspace with ApprovalRequirement::Auto, meaning it runs without any user approval prompt. cargo test compiles and executes arbitrary code: test binaries, build.rs build scripts, and proc macros. While auto-approving test execution is a deliberate design choice, it creates an inconsistency in the security boundary. However, in a malicious repository, test code can execute arbitrary shell commands, exfiltrate credentials, or establish persistence with zero approval. The attack is amplified by AGENTS.md (auto-loaded into the system prompt), which can instruct the model to run tests proactively at session start. This vulnerability is fixed in 0.8.23."},{"lang":"es","value":"CodeWhale es un agente de codificación DeepSeek + MiMo en terminal. Desde la versión 0.3.0 hasta la 0.8.23, la herramienta run_tests ejecuta cargo test en el espacio de trabajo con ApprovalRequirement::Auto, lo que significa que se ejecuta sin ninguna solicitud de aprobación del usuario. cargo test compila y ejecuta código arbitrario: binarios de prueba, scripts de compilación build.rs y proc macros. Aunque la aprobación automática de la ejecución de pruebas es una elección de diseño deliberada, crea una inconsistencia en el límite de seguridad. Sin embargo, en un repositorio malicioso, el código de prueba puede ejecutar comandos de shell arbitrarios, exfiltrar credenciales o establecer persistencia sin ninguna aprobación. El ataque se amplifica por AGENTS.md (cargado automáticamente en el system prompt), que puede instruir al modelo para que ejecute pruebas de forma proactiva al inicio de la sesión. Esta vulnerabilidad se corrige en la versión 0.8.23."}],"affected":[{"source":"security-advisories@github.com","affectedData":[{"vendor":"Hmbown","product":"CodeWhale","versions":[{"version":">= 0.3.0, < 0.8.23","status":"affected"}]}]}],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H","baseScore":9.6,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"CHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":2.8,"impactScore":6.0}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-06-01T19:09:32.481506Z","id":"CVE-2026-45311","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"weaknesses":[{"source":"security-advisories@github.com","type":"Secondary","description":[{"lang":"en","value":"CWE-94"}]}],"references":[{"url":"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wx44-2q6h-j6p8","source":"security-advisories@github.com"},{"url":"https://github.com/Hmbown/CodeWhale/security/advisories/GHSA-wx44-2q6h-j6p8","source":"134c704f-9b21-4f2e-91b3-4a467353bcc0"}]}