CVE-2026-77956

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.

CVSS

No CVSS.

References

Link	Resource
https://cna.erlef.org/cves/CVE-2026-77956.html
https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514
https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83
https://osv.dev/vulnerability/EEF-CVE-2026-77956
https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-31 01:16

Updated : 2026-09-01 21:15

NVD link : CVE-2026-77956

Mitre link : CVE-2026-77956

CVE.ORG link : CVE-2026-77956

JSON object : View

Products Affected

No product.

CWE

CWE-94

Improper Control of Generation of Code ('Code Injection')

{"id": "CVE-2026-77956", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-77956", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-31T16:01:20.485407Z"}}], "cvssMetricV40": [{"type": "Secondary", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 8.9, "Automatable": "NOT_DEFINED", "attackVector": "LOCAL", "baseSeverity": "HIGH", "valueDensity": "NOT_DEFINED", "vectorString": "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", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "PRESENT", "privilegesRequired": "NONE", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "vulnConfidentialityImpact": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db", "affectedData": [{"cpes": ["cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"], "repo": "https://github.com/ash-project/ash_ai", "vendor": "ash-project", "modules": ["'Elixir.AshAi.Actions.Prompt'"], "product": "ash_ai", "versions": [{"status": "affected", "version": "0.1.0", "lessThan": "1.0.0", "versionType": "semver"}], "packageURL": "pkg:hex/ash_ai", "packageName": "ash_ai", "programFiles": ["lib/ash_ai/actions/prompt.ex"], "collectionURL": "https://repo.hex.pm", "defaultStatus": "unaffected", "programRoutines": [{"name": "'Elixir.AshAi.Actions.Prompt':build_context/3"}]}, {"cpes": ["cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"], "repo": "https://github.com/ash-project/ash_ai", "vendor": "ash-project", "modules": ["'Elixir.AshAi.Actions.Prompt'"], "product": "ash_ai", "versions": [{"status": "affected", "version": "4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1", "lessThan": "e9948254b5659c1143b73dc2f59f457931e64514", "versionType": "git"}], "packageURL": "pkg:github/ash-project/ash_ai", "packageName": "ash-project/ash_ai", "programFiles": ["lib/ash_ai/actions/prompt.ex"], "collectionURL": "https://github.com", "defaultStatus": "unaffected", "programRoutines": [{"name": "'Elixir.AshAi.Actions.Prompt':build_context/3"}]}]}], "published": "2026-08-31T01:16:49.563", "references": [{"url": "https://cna.erlef.org/cves/CVE-2026-77956.html", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"}, {"url": "https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"}, {"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"}, {"url": "https://osv.dev/vulnerability/EEF-CVE-2026-77956", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"}, {"url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db", "description": [{"lang": "en", "value": "CWE-94"}]}], "descriptions": [{"lang": "en", "value": "Improper Control of Generation of Code (Code Injection) vulnerability in ash-project ash_ai allows a remote, unauthenticated client to execute arbitrary Elixir code.\n\nAshAi.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.\n\nThis issue affects ash_ai: from 0.1.0 before 1.0.0."}], "lastModified": "2026-09-01T21:15:00.147", "sourceIdentifier": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db"}