Vulnerability · Published Aug 31, 2026 · Assigned by EEF
CVE-2026-77956EEx template evaluation of prompt content in AshAi enables remote code execution
High 8.9
In plain English
A high-severity code injection in ash_ai from ash-project. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 21% of all known vulnerabilities).
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| ash-project | ash_ai | 0.1.0 – before 1.0.0 |
| ash-project | ash_ai | 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 – before e9948254b5659c1143b73dc2f59f457931e64514 |
Weakness: CWE-94 · Vector: 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
References
- https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83 vendor-advisory, related
- https://cna.erlef.org/cves/CVE-2026-77956.html related
- https://osv.dev/vulnerability/EEF-CVE-2026-77956 related
- https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514 patch