Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-77956— EEx template evaluation of prompt content in AshAi enables remote code execution

Quick assessment

Affected
ash-project ash_ai
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Ash Framework Ash AI是Ash Framework组织的一款机器学习产品。 Ash Framework Ash AI 0.1.0版本至1.0.0之前版本存在代码注入漏洞，该漏洞源于对prompt内容的代码生成控制不当，通过EEx.eval_string/2评估用户可控内容，可能导致远程未认证客户端执行任意Elixir代码。

CVSS 8.9 · High EPSS 0.28% · P19

Affected Version Matrix 2

VendorProduct Version RangeStatus
ash-project ash_ai 0.1.0< 1.0.0 affected
4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1< e9948254b5659c1143b73dc2f59f457931e64514 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-77956

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
EEx template evaluation of prompt content in AshAi enables remote code execution
Source: CVE Program / CVE List V5
Vulnerability 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: CVE Program / CVE List V5
CVSS Information
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
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
Ash Framework Ash AI 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Ash Framework Ash AI是Ash Framework组织的一款机器学习产品。 Ash Framework Ash AI 0.1.0版本至1.0.0之前版本存在代码注入漏洞，该漏洞源于对prompt内容的代码生成控制不当，通过EEx.eval_string/2评估用户可控内容，可能导致远程未认证客户端执行任意Elixir代码。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
ash-project ash_ai 0.1.0 ~ 1.0.0 cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*
ash-project ash_ai 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 ~ e9948254b5659c1143b73dc2f59f457931e64514 cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*

II. Public POCs for CVE-2026-77956

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-77956

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-77956 (1)

Vendor Advisories for CVE-2026-77956 (2)

Other References for CVE-2026-77956 (1)

Same Patch Batch · ash-project · 2026-08-31 · 17 CVEs total

CVE-2026-77850 8.4 HIGH Stored XSS in AshAdmin relationship typeahead via unescaped label_field content
CVE-2026-75757 8.3 HIGH AshAdmin cookie reader matches names by substring, enabling actor/session shadowing from a
CVE-2026-82722 8.3 HIGH AshAdmin LiveView events intern atoms from client input, exhausting the atom table (node D
CVE-2026-82673 8.3 HIGH Path traversal in AshAdmin file uploads via unsanitized client filename
CVE-2026-82724 7.6 HIGH Broken access control in AshPhoenix SubdomainHook via a nil tenant in handle_subdomain
CVE-2026-81315 7.4 HIGH MCP DNS-rebinding origin check in AshAi is bypassed by a spoofed X-Forwarded-Proto header
CVE-2026-75760 7.1 HIGH AshAi vectorize change leaks raw embedding-provider errors, including credentials, in a us
CVE-2026-82564 7.1 HIGH Identity tool filter in AshAi accepts operator maps, allowing update or destroy of unident
CVE-2026-82726 6.3 MEDIUM AshPhoenix get_subdomain maps a crafted or differently-cased Host header to an arbitrary t
CVE-2026-82579 6.0 MEDIUM AshAi tool loop never terminates when all tool calls are filtered out, enabling denial of
CVE-2026-82580 5.3 MEDIUM AshAi echoes raw tool exception messages into the conversation, disclosing internal detail
CVE-2026-81853 2.3 LOW AshAdmin composite primary key decoding accepts arbitrary fields, enabling a secret-attrib
CVE-2026-82725 2.3 LOW AshPhoenix FilterForm allows filtering across non-public relationships, disclosing private
CVE-2026-82727 2.3 LOW AshPhoenix Form.Auto leaks submitted params in an unknown _union_type error message
CVE-2026-81852 2.1 LOW AshAdmin ships a hardcoded CSP nonce, allowing nonce-based CSP bypass
CVE-2026-82681 2.0 LOW Query-parameter injection in AshAdmin row-action links via unencoded string primary keys

IV. Related Vulnerabilities

Same product: ash_ai
Same vendor: ash-project
Same weakness: CWE-94

V. Comments for CVE-2026-77956

No comments yet

Leave a comment