CVE-2026-77956: CWE-94 Improper Control of Generation of Code ('Code Injection') in ash-project ash_ai
Description
CVE-2026-77956 is a high-severity code injection vulnerability in ash-project's ash_ai component. It allows a remote, unauthenticated attacker to execute arbitrary Elixir code by exploiting the evaluation of prompt content as EEx templates. The vulnerability affects versions from 0.1.0 up to but not including 1.0.0. The issue arises because attacker-controlled input can be compiled and executed on the server without authentication. The fix involves stopping the evaluation of function-supplied prompt content as EEx templates, limiting evaluation to statically configured templates only.
CVSS v4.0
Score 8.9high
Affected software
ash-project
ash_ai
ash-project
ash_ai
cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability (CVE-2026-77956) in ash_ai arises from improper control over code generation (CWE-94). The component AshAi.Actions.Prompt uses EEx.eval_string/2 to evaluate prompt content, which can be constructed from action arguments including attacker-controlled data. This allows remote, unauthenticated clients to inject and execute arbitrary Elixir code on the server by embedding malicious EEx templates such as <%= System.cmd(...) %>. The vulnerability affects all versions from 0.1.0 before 1.0.0. The remediation involves ceasing evaluation of dynamic function-supplied prompt content as EEx templates, restricting evaluation to only static templates.
Potential Impact
An unauthenticated remote attacker can execute arbitrary Elixir code on the server running ash_ai, potentially leading to full system compromise. This includes executing system commands before any model request is processed. The vulnerability has a CVSS 4.0 score of 8.9 (high severity), indicating significant impact on confidentiality, integrity, and availability.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. The described fix is to stop evaluating function-supplied prompt content as EEx templates and only evaluate statically configured templates. Until an official patch or update is released, avoid exposing prompt actions that incorporate untrusted input or disable dynamic prompt evaluation if possible.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- EEF
- Date Reserved
- 2026-08-30T17:30:01.409Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 6a94d3dbacd9273b49511802
Added to database: 08/31/2026, 01:07:39 UTC
Last enriched: 09/07/2026, 15:39:50 UTC
Last updated: 10/13/2026, 06:48:19 UTC
Views: 92
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.