Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-77956 – Remote Code Execution – ash_ai (ash-project) versions 0.1.0 to before 1.0.0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-77956 is a critical code injection vulnerability in ash_ai, the Elixir library that provides structured outputs, vectorization, and tool calling for Ash Framework applications. The flaw resides in the AshAi.Actions.Prompt module, which evaluates prompt content as an EEx (Embedded Elixir) template, allowing an unauthenticated remote attacker to inject and execute arbitrary Elixir code on the host application. The vulnerability carries a maximum CVSS v3.1-equivalent score of 10.0 (Critical) and requires no authentication or user interaction to exploit.

Technical details

  • Root cause: AshAi.Actions.Prompt passes prompt content through EEx.eval_string/2 without sanitization or escaping before sending it to the LLM. Any prompt that does not return a ReqLLM.Context object is compiled and executed as Elixir source code.
  • Trigger conditions: An application that builds AI prompts from strings or functions incorporating user-supplied/request data (rather than constructing a ReqLLM.Context object) is vulnerable. Three sobelow_skip annotations in the code suppressed static-analysis warnings about this pattern rather than mitigating it.
  • Attack vector: Network — an unauthenticated attacker submits text containing EEx expressions (e.g., <%= System.cmd(...) %>) to any HTTP endpoint that forwards user input into an AshAi prompt action. The malicious EEx template is evaluated and executed before any request is even sent to the underlying LLM.
  • Impact: Full remote code execution in the context of the running application/server process, with complete loss of confidentiality, integrity, and availability.

Affected software

  • Package: ash_ai (ash-project)
  • Vulnerable versions: >= 0.1.0, < 1.0.0
  • Fixed version: 1.0.0

Severity

  • CVSS Score: 10.0 (Critical)
  • CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
  • CWE: CWE-94 (Improper Control of Generation of Code / Code Injection)

Mitigation and recommended actions

  • Immediate: Upgrade ash_ai to version 1.0.0 or later, which removes the unsafe EEx.eval_string/2 evaluation of prompt content.
  • If immediate patching is not possible:
    • Construct all AshAi prompts as ReqLLM.Context objects instead of raw strings or functions that assemble content from user-supplied/request data — prompts returning ReqLLM.Context bypass the vulnerable EEx evaluation path.
    • Audit all AshAi Actions.Prompt usages for any path where request or user-controlled data flows into prompt strings, and remove or sanitize such flows until the upgrade can be applied.
    • Treat any application using ash_ai prompt actions with untrusted input as high risk and restrict network exposure until patched.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge