Skip to content
Threat Brief

← All advisories

CVE-2026-77956

High 8.9No known exploitationFix available

EEx template evaluation of prompt content in AshAi enables remote code execution

Record last updated

CVSS score

8.9

High on a 0 to 10 scale

EPSS, chance of exploitation in 30 days

0.4%

Higher than 29% of scored CVEs. A prediction, not evidence.

CISA remediation deadline

None

Not in the KEV catalog

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 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.

Weakness: CWE-94

Patching and mitigation

Patch status
Fix available (source: CVE record (EEF))
Fix documented (source date)
Mitigation
None documented
Vendor guidance
github.com (opens in a new tab)

Affected products

VendorProductAffected versionsFixed inPer
ash-projectash_aifrom 0.1.0 before 1.0.01.0.0CVE Program
ash-projectash_aifrom 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 before e9948254b5659c1143b73dc2f59f457931e64514e9948254b5659c1143b73dc2f59f457931e64514CVE Program

Timeline

  1. Disclosure

    CVE record published by EEF

    Source: CVE Program (opens in a new tab)

  2. Patch

    Fix documented by CVE record (EEF)

    Source: CVE record (EEF) (opens in a new tab)

Vendor guidance and references