Skip to content

CVE-2026-77956 EEx template evaluation of prompt content in AshAi enables remote code execution

HighCVSS 8.9 EPSS 0.35%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
Proof of concept public · automatable: no · technical impact: total

Description

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.

Upgrade path

1 package: 1 fixed.

PackageAffectedFixed inStatus
ash-project ash ai >= 0.1.0, < 1.0.0; >= 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1, < e9948254b5659c1143b73dc2f59f457931e64514 1.0.0, e9948254b5659c1143b73dc2f59f457931e64514 Fixed

Affected products

ProductAffected versionsFixed in
ash-project ash ai >= 0.1.0, < 1.0.0 1.0.0
ash-project ash ai >= 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1, < e9948254b5659c1143b73dc2f59f457931e64514 e9948254b5659c1143b73dc2f59f457931e64514

References