ash_ai: Improper Control of Generation of Code
CVE-2026-77956 is a high-severity improper control of generation of code vulnerability in ash_ai from Ash-project, with a CVSS 4.0 base score of 8.9 out of 10. It can be exploited with local access to the system by an unauthenticated attacker, without any action from a user. The record lists versions 1.0.0, e9948254b5659c1143b73dc2f59f457931e64514 as the first without the flaw, so updating ash_ai to one of those releases or later removes the exposure. There is no confirmed exploitation so far. EPSS estimates a 0.28% chance of exploitation within 30 days, which is low compared with other CVEs.
High severity with no evidence of exploitation so far.
What to do
- Update ash_ai to 1.0.0 or e9948254b5659c1143b73dc2f59f457931e64514, whichever matches your release line, or a later version.
- Read the advisory on github.com for workarounds and exact fixed builds.
Affected products and versions
| Vendor | Product | Affected versions | Fixed in |
|---|---|---|---|
| Ash-project | ash_ai | 0.1.0 up to, but not including, 1.0.0; 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 up to, but not including, e9948254b5659c1143b73dc2f59f457931e64514 | 1.0.0, e9948254b5659c1143b73dc2f59f457931e64514 |
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- LocalThe attacker needs local access or must trick a user into running something.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Attack requirements
- PresentThe target must be in a specific state or configuration for the attack to work.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Confidentiality (vulnerable system)
- HighSerious loss of confidentiality on the vulnerable system.
- Integrity (vulnerable system)
- HighSerious loss of integrity on the vulnerable system.
- Availability (vulnerable system)
- HighSerious loss of availability on the vulnerable system.
- Confidentiality (other systems)
- HighSerious loss of confidentiality on systems beyond the vulnerable one.
- Integrity (other systems)
- HighSerious loss of integrity on systems beyond the vulnerable one.
- Availability (other systems)
- HighSerious loss of availability on systems beyond the vulnerable one.
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. Scored by CNA.
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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Improper Control of Generation of Code
The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
How developers prevent this class of flaw
- Refactor your program so that you do not have to dynamically generate code.
- Run your code in a jail or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict which code can be executed by your product. Examples include the Unix chroot jail and AppArmor. In general, managed code may provide some protection. This may not be a feasible solution, and it only limits the impact to the operating system; the rest of your application may still be subject to compromise. Be careful to avoid CWE-243 and other weaknesses related to jails.
- Use dynamic tools and techniques that interact with the product using large test suites with many diverse inputs, such as fuzz testing (fuzzing), robustness testing, and fault injection. The product's operation may slow down, but it should not become unstable, crash, or generate incorrect results.
More Improper Control of Generation of Code vulnerabilities (CWE-94)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: poc, automatable: no, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Patches and release notes
Other vulnerabilities in ash_ai
- 7.1 High severity
- 7.1 High severity
- 7.4 High severity
Recent Improper Control of Generation of Code vulnerabilities
- 9.8 Critical severity
- 8.8 High severity
- 8.8 High severity
- 9.9 Critical severity
- 9.8 Critical severity
- 9.1 Critical severity
Spotted an error? Tell us.