CVE-2026-77956
EEx template evaluation of prompt content in AshAi enables remote code execution
CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Fuente: CNA
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Divulgación | Publicada | CVE-2026-77956 divulgada · CVSS 8.9 (CNA) | |
| Divulgación | Evaluación SSVC | CISA-ADP · explotación PoC pública | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
Improper Control of Generation of Code (Code Injection) vulnerability in ash-project ash_ai allows a remote, unauthenticated client to execute arbitrary Elixir code. AshAi.Actions.Prompt evaluates prompt content through EEx.eval_string/2. The documented prompt: fn input, context -> ... end form lets the prompt content be built from action arguments, so when a prompt action's text incorporates request data, that attacker-controlled text is compiled and run as an EEx template (Elixir source). Content such as <%= System.cmd(...) %> therefore executes on the server before any model request is made, requiring no authentication beyond reaching a prompt action. The fix stops evaluating function-supplied prompt content as EEx; only statically configured templates are evaluated. This issue affects ash_ai: from 0.1.0 before 1.0.0.
Desglose de métricas
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
ash_ai |
Corregida | 1.0.0 | — | — |
1.0.0Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514https://cna.erlef.org/cves/CVE-2026-77956.htmlhttps://osv.dev/vulnerability/EEF-CVE-2026-77956Las referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
