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.
- Products
- Not specified
- Affected versions
- Not specified
- Fixed versions
- Not specified
- CVEs
- CVE-2026-77956
- Confirmed fixed CVEs
- Not specified
- Updated in this feed
- 4 Nov 2026, 14:04 UTC · Revision 1
Source evidence
EEx template evaluation of prompt content in AshAi enables remote code execution
core-osv · Original sourcePublished 31 Aug 2026, 00:56 UTC
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.
osv:CVE-2026-77956
Complete source record
{
"id": "8bd2fd541437e7d9d6c410169538624d291270c42abf2ed65bc2e82e4c38723c",
"url": "https://osv.dev/vulnerability/CVE-2026-77956",
"method": "structured",
"payload": {
"kind": "advisory",
"title": "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.",
"evidence": "osv:CVE-2026-77956",
"products": [],
"severity": "high",
"structured": {
"id": "CVE-2026-77956",
"aliases": [
"CVE-2026-77956",
"EEF-CVE-2026-77956",
"GHSA-2g59-hg7m-qc83"
],
"metrics": [
{
"type": "CVSS_V4",
"score": "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"
}
],
"affected": [
{
"ranges": [
{
"repo": "https://github.com/ash-project/ash_ai",
"type": "GIT",
"events": [
{
"introduced": "4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1"
},
{
"fixed": "e9948254b5659c1143b73dc2f59f457931e64514"
},
{
"introduced": "9be71660e448d601b6b5d1846d227c0b52fb64ac"
},
{
"fixed": "f72b14744996e71df6d73480d617d963f340597b"
}
],
"database_specific": {
"extracted_events": [
{
"range": [
{
"introduced": "4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1"
},
{
"fixed": "e9948254b5659c1143b73dc2f59f457931e64514"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"range": [
{
"introduced": "0.1.0"
},
{
"fixed": "1.0.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
},
{
"range": [
{
"fixed": "e9948254b5659c1143b73dc2f59f457931e64514"
}
],
"source": "REFERENCES_COMMIT"
}
]
}
}
],
"versions": [
"v0.8.2",
"v0.8.1",
"v0.8.0",
"v0.7.3",
"v0.7.2",
"v0.7.1",
"v0.7.0",
"v0.6.1",
"v0.6.0",
"v0.5.0",
"v0.4.0",
"v0.3.0",
"v0.2.14",
"v0.2.13",
"v0.2.12",
"v0.2.11",
"v0.2.10",
"v0.2.9",
"v0.2.8",
"v0.2.7",
"v0.2.6",
"v0.2.5",
"v0.2.4",
"v0.2.3",
"v0.2.2",
"v0.2.1",
"v0.1.11",
"v0.1.10",
"v0.1.9",
"v0.1.8",
"v0.1.7",
"v0.1.6",
"v0.1.5",
"v0.1.4",
"v0.1.3",
"v0.1.2",
"v0.1.1",
"v0.1.0"
],
"database_specific": {
"source": "https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-77956.json"
}
}
],
"modified": "2026-10-28T02:30:36.092767981Z",
"provider": "osv",
"references": [
"https://cna.erlef.org/cves/CVE-2026-77956.html",
"https://github.com",
"https://osv.dev/vulnerability/EEF-CVE-2026-77956",
"https://repo.hex.pm",
"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/77xxx/CVE-2026-77956.json",
"https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83",
"https://nvd.nist.gov/vuln/detail/CVE-2026-77956",
"https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514",
"https://github.com/ash-project/ash_ai"
],
"provider_metadata": {
"cwe_ids": [
"CWE-94"
],
"cna_assigner": "EEF",
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/77xxx/CVE-2026-77956.json"
}
},
"related_cves": [
{
"value": "CVE-2026-77956",
"evidence": "/id"
}
],
"security_relevant": true,
"severity_evidence": "/severity/0/score"
},
"source_id": "core-osv",
"document_id": 503391,
"published_at": "2026-08-31T00:56:26.44+00:00"
}