Unauthenticated code execution via EEx prompt evaluation
Published Aug 31, 2026 · Updated Aug 31, 2026
Code injection in Ash AI before 1.0.0 allows remote attackers to execute arbitrary Elixir code through a reachable prompt action. AshAi.Actions.Prompt passes function-supplied prompt content derived from action arguments to EEx.eval_string/2, compiling attacker-controlled text as an Elixir template. Exposure requires an application to place request data in prompt text and expose that action across an untrusted boundary; execution occurs in the application's BEAM node before any model request.
Summary
What happened
Code injection in Ash AI before 1.0.0 allows remote attackers to execute arbitrary Elixir code through a reachable prompt action. AshAi.Actions.Prompt passes function-supplied prompt content derived from action arguments to EEx.eval_string/2, compiling attacker-controlled text as an Elixir template. Exposure requires an application to place request data in prompt text and expose that action across an untrusted boundary; execution occurs in the application's BEAM node before any model request.
The record
- CVE
- CVE-2026-77956
- Published
- Aug 31, 2026
- Updated
- Aug 31, 2026
- Vendor
- Ash Framework
- Product
- Ash AI
- Classifications
- CWE-94, T1059, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 31, 2026CVE publishedPublication date reported by the CVE source.
- Aug 31, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.1.0 <1.0.0
- Affected versionversion=4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 <e9948254b5659c1143b73dc2f59f457931e64514
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-2g59-hg7m-qc83 HTTP prompt-action proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo