EUVD-2026-68303Severity by source
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
Network-reachable unauthenticated endpoint; exploitation trivial once vulnerable prompt action exists; full RCE yields scope change to OS level (S:C).
Primary rating from Vendor (EEF).
CVSS VectorVendor: EEF
Lifecycle Timeline
8DescriptionCVE.org
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.
AnalysisAI
Remote code execution in ash_ai (versions 0.1.0 through pre-1.0.0) allows unauthenticated network attackers to execute arbitrary Elixir code on the server by submitting EEx template payloads through prompt action arguments. The AshAi.Actions.Prompt module incorrectly passed function-supplied prompt content - which is frequently assembled from user-controlled action arguments - through EEx.eval_string/2 before forwarding to the AI model, meaning payloads like <%= System.cmd("id", []) %> execute server-side with application process privileges. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | The target application must use ash_ai and define at least one Ash action with the function-form prompt configuration (prompt: fn input, context -> ... … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The vendor-assigned CVSS 4.0 score of 8.9 is directionally reasonable given the full-RCE outcome, but the provided vector contains a material discrepancy: AV:L (local attack vector) directly contradicts the description's explicit assertion of 'remote, unauthenticated client' exploitation - a network-reachable HTTP endpoint cannot carry a local attack vector, and this appears to be a scoring error. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | Upgrade ash_ai to version 1.0.0 or later, which contains the fix at commit e9948254b5659c1143b73dc2f59f457931e64514; this is the only confirmed vendor-released patch. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, identify all systems and applications running ash_ai versions 0.1.0 through pre-1.0.0 and download the vendor-released patch; test the patch in a non-production environment to confirm application compatibility. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
DNS-rebinding protection in AshAi.Mcp.Server (ash_ai 0.8.0-0.x) is bypassable because the default origin check trusts th
Authorization bypass in AshAi (ash_ai) versions 0.6.0 through pre-1.0.0 allows any authenticated tool caller to update o
Credential leakage in ash_ai (versions 0.1.0 through before 1.0.0) exposes embedding provider API keys and request inter
Infinite-loop denial-of-service in ash_ai's ToolLoop component (versions 0.6.0 through <1.0.0) allows an attacker who ca
Field policy bypass in ash_ai (versions 0.1.0 through < 1.0.3) allows authenticated, low-privilege actors to read per-ac
Unfiltered exception serialization in ash_ai 0.6.0-0.x leaks internal application details - database schema, raw SQL fra
Same weakness CWE-94 – Code Injection
View allShare
External POC / Exploit Code
Leaving vuln.today