ash_ai vulnerabilities

4 known vulnerabilities in ash_ai from Ash-project. 4 are rated high or critical. Each entry lists the affected versions and the release that fixes it, where the vendor has published one.

Latest first

• 7.1 High severity

  ash_ai: Authorization Bypass Through User-Controlled Key

  CVE-2026-82564Aug 31, 2026Ash-project

  Authorization Bypass Through User-Controlled Key vulnerability in ash-project ash_ai allows a caller of an identity-configured tool to update or destroy records it never identified, including every row in the table. In AshAi.Tool.Execution, identity_filter/3 b

• 7.1 High severity

  ash_ai: Generation of Error Message Containing Sensitive Information

  CVE-2026-75760Aug 31, 2026Ash-project

  Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai discloses provider request state and credentials in a user-facing validation error. In AshAi.Changes.Vectorize, when the embedding provider call fails the change a

• 7.4 High severity

  ash_ai: Origin Validation Error

  CVE-2026-81315Aug 31, 2026Ash-project

  Origin Validation Error vulnerability in ash-project ash_ai allows a malicious web page to bypass the MCP server's DNS-rebinding protection and issue cross-site requests to a user's local MCP server with that user's actor. In AshAi.Mcp.Server, with the default

• 8.9 High severity

  ash_ai: Improper Control of Generation of Code

  CVE-2026-77956Aug 31, 2026Ash-project

  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