CVE-2026-77956
EEx template evaluation of prompt content in AshAi enables remote code execution
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.
Attack profile
How easy it is to exploit
- Attack vector
- Local
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
EEx template evaluation of prompt content in AshAi enables remote code execution
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.
- Record
CVE-2026-77956- CVSS 4.0
- 8.9 High
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 - Weakness
- CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2026-68303
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.
- Record
EUVD-2026-68303- CVSS 4.0
- 8.9 High
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 - Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-77956- CVSS 4.0
- 8.9 High
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 - Weakness
- CWE-94
- Updated
- 2026-11-02
OSV
EEx template evaluation of prompt content in AshAi enables remote code execution
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.
- Record
CVE-2026-77956- CVSS 4.0
- 8.9 High
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 - Weakness
- CWE-94
- Updated
- 2026-11-02
OSVEEF-CVE-2026-77956
EEx template evaluation of prompt content in AshAi enables remote code execution
Summary
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.
- Record
EEF-CVE-2026-77956- CVSS 4.0
- 8.9 High
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 - Weakness
- CWE-94
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
ash_aiHex |
0.1.0 up to 1.0.0, plus listed versions 0.1.10.1.100.1.110.1.30.1.4 Show 32 moreShow less0.1.50.1.60.1.70.1.80.1.90.2.00.2.10.2.100.2.110.2.120.2.130.2.140.2.20.2.30.2.40.2.50.2.60.2.70.2.80.2.90.3.00.4.00.5.00.6.00.6.10.7.00.7.10.7.20.7.30.8.00.8.10.8.2 |
1.0.0 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-77956 is a high vulnerability (CVSS 8.9) in Ash-project Ash Ai, published August 31, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.28%, the 20th percentile. Fixed in ash_ai 1.0.0.