EEx template evaluation of prompt content in AshAi enables remote code execution
Key facts
- Attack vector
- Local
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- Present
- Impact type
- Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA. Impact type from CWE-94.
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| ash-project | ash_ai | 0.1.0 to before 1.0.0 | 1.0.0 | Patch available | CNA |
- ash_ai Vendorash-project Affected 0.1.0 to before 1.0.0 Fixed in 1.0.0 Patch available CNA
CPE names CNA · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:* | — | — | — |
- cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:* Versions — — ·—
Remediation
- Fix · CNA ash_ai (ash-project) Fixed in 1.0.0
Fixed in the same release
Records fixed by the same vendor advisory or release, as the CNA lists them.
- Release ·
ash-project ash_ai 1.0.0
6 records Highest priority Priority HIGH 2 HIGH, 4 MEDIUM
Other records, highest priority first
- TI-2026-56145 MCP DNS-rebinding origin check in AshAi is bypassed by a spoofed X-Forwarded-Proto headerPriority HIGH 68
- TI-2026-56918 Identity tool filter in AshAi accepts operator maps, allowing update or destroy of unidentified recordsPriority MEDIUM 64
- TI-2026-53035 AshAi vectorize change leaks raw embedding-provider errors, including credentials, in a user-facing errorPriority MEDIUM 64
Timeline
- 2026-10-02 Threatist record created from CVE-2026-77956
References
More ash-project vulnerabilities
- TI-2026-56298 Query-complexity limit bypass via first/last pagination arguments in AshGraphql enables denial of service CVSS 4.0HIGH 8.7
- TI-2026-52572 Unbounded atom creation from client-supplied RPC field names in AshTypescript field formatter CVSS 4.0HIGH 8.7
- TI-2026-57010 Path traversal in AshAdmin file uploads via unsanitized client filename CVSS 4.0HIGH 8.3
- TI-2026-26840 Ash Framework: Ash.Type.Module.cast_input/2 atom exhaustion via unchecked Module.concat allows BEAM VM crash CVSS 4.0HIGH 8.2
- TI-2026-54208 Stored XSS in AshAdmin relationship typeahead via unescaped label_field content CVSS 4.0HIGH 8.4
- TI-2026-56295 Unhandled KeyError in AshGraphql relay node resolution crashes queries via an unknown type segment CVSS 4.0MEDIUM 6.9
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences