CVE-2026-119613 (GCVE-0-2026-119613)

Vulnerability from cvelistv5 – Published: 2026-11-09 13:03 – Updated: 2026-11-09 13:03
VLAI
Title
AshAi sends unrecognized tool errors verbatim to MCP clients and the model, disclosing internal details
Summary
Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail. AshAi.ToToolError gained an implementation for Ash.Error.Unknown.UnknownError that returns the error's error field as is, and AshAi.Tool.Errors.format/1 sends that text to MCP clients (tool calls and resource reads in AshAi.Mcp.Server) and to the model in AshAi.ToolLoop. Ash stores the full Exception.format/2 output of a raised exception, or inspect/1 of a bare {:error, term} return, in that field. A tool result that cannot be JSON-encoded raises a Protocol.UndefinedError whose text includes the inspected value, which can be a whole record with fields the tool never returns. None of these errors were logged. The fix logs them under an error id and returns only that id to the caller. This issue affects ash_ai: from 1.5.0 before 1.5.1.
CWE
  • CWE-209 - Generation of Error Message Containing Sensitive Information
Assigner
EEF CNA
Impacted products
Vendor Product Version
ash-project ash_ai Affected: 1.5.0 , < 1.5.1 (semver)
    cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*
Create a notification for this product.
ash-project ash_ai Affected: fbad04e9620ef70603f4e67e03f15092f58578f6 , < af7987769d78ed070c8a9f6e6ee542d91744eae6 (git)
    cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*
Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "cna": {
      "affected": [
        {
          "collectionURL": "https://repo.hex.pm",
          "cpes": [
            "cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
          ],
          "defaultStatus": "unaffected",
          "modules": [
            "\u0027Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError\u0027",
            "\u0027Elixir.AshAi.Tool.Errors\u0027",
            "\u0027Elixir.AshAi.Mcp.Router\u0027",
            "\u0027Elixir.AshAi.ToolLoop\u0027"
          ],
          "packageName": "ash_ai",
          "packageURL": "pkg:hex/ash_ai",
          "product": "ash_ai",
          "programFiles": [
            "lib/ash_ai/to_tool_error.ex",
            "lib/ash_ai/tool/errors.ex",
            "lib/ash_ai/mcp/router.ex",
            "lib/ash_ai/tool_loop.ex"
          ],
          "programRoutines": [
            {
              "name": "\u0027Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError\u0027:to_tool_error/1"
            },
            {
              "name": "\u0027Elixir.AshAi.Tool.Errors\u0027:format/1"
            },
            {
              "name": "\u0027Elixir.AshAi.Mcp.Router\u0027:call/2"
            },
            {
              "name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
            }
          ],
          "repo": "https://github.com/ash-project/ash_ai",
          "vendor": "ash-project",
          "versions": [
            {
              "lessThan": "1.5.1",
              "status": "affected",
              "version": "1.5.0",
              "versionType": "semver"
            }
          ]
        },
        {
          "collectionURL": "https://github.com",
          "cpes": [
            "cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"
          ],
          "defaultStatus": "unaffected",
          "modules": [
            "\u0027Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError\u0027",
            "\u0027Elixir.AshAi.Tool.Errors\u0027",
            "\u0027Elixir.AshAi.Mcp.Router\u0027",
            "\u0027Elixir.AshAi.ToolLoop\u0027"
          ],
          "packageName": "ash-project/ash_ai",
          "packageURL": "pkg:github/ash-project/ash_ai",
          "product": "ash_ai",
          "programFiles": [
            "lib/ash_ai/to_tool_error.ex",
            "lib/ash_ai/tool/errors.ex",
            "lib/ash_ai/mcp/router.ex",
            "lib/ash_ai/tool_loop.ex"
          ],
          "programRoutines": [
            {
              "name": "\u0027Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError\u0027:to_tool_error/1"
            },
            {
              "name": "\u0027Elixir.AshAi.Tool.Errors\u0027:format/1"
            },
            {
              "name": "\u0027Elixir.AshAi.Mcp.Router\u0027:call/2"
            },
            {
              "name": "\u0027Elixir.AshAi.ToolLoop\u0027:run/2"
            }
          ],
          "repo": "https://github.com/ash-project/ash_ai",
          "vendor": "ash-project",
          "versions": [
            {
              "lessThan": "af7987769d78ed070c8a9f6e6ee542d91744eae6",
              "status": "affected",
              "version": "fbad04e9620ef70603f4e67e03f15092f58578f6",
              "versionType": "git"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "1.5.1",
                  "versionStartIncluding": "1.5.0",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ],
          "operator": "AND"
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Sebastian Seilund"
        },
        {
          "lang": "en",
          "type": "reporter",
          "value": "Sebastian Seilund"
        },
        {
          "lang": "en",
          "type": "remediation developer",
          "value": "Zach Daniel / Ash Project"
        },
        {
          "lang": "en",
          "type": "coordinator",
          "value": "Jonatan M\u00e4nnchen / EEF"
        }
      ],
      "dateAssigned": "2026-11-07T21:44:36.000Z",
      "descriptions": [
        {
          "lang": "en",
          "supportingMedia": [
            {
              "base64": false,
              "type": "text/html",
              "value": "\u003cp\u003eGeneration of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail.\u003c/p\u003e\n\u003cp\u003e\u003ccode\u003eAshAi.ToToolError\u003c/code\u003e gained an implementation for \u003ccode\u003eAsh.Error.Unknown.UnknownError\u003c/code\u003e that returns the error\u0027s \u003ccode\u003eerror\u003c/code\u003e field as is, and \u003ccode\u003eAshAi.Tool.Errors.format/1\u003c/code\u003e sends that text to MCP clients (tool calls and resource reads in \u003ccode\u003eAshAi.Mcp.Server\u003c/code\u003e) and to the model in \u003ccode\u003eAshAi.ToolLoop\u003c/code\u003e. Ash stores the full \u003ccode\u003eException.format/2\u003c/code\u003e output of a raised exception, or \u003ccode\u003einspect/1\u003c/code\u003e of a bare \u003ccode\u003e{:error, term}\u003c/code\u003e return, in that field. A tool result that cannot be JSON-encoded raises a \u003ccode\u003eProtocol.UndefinedError\u003c/code\u003e whose text includes the inspected value, which can be a whole record with fields the tool never returns. None of these errors were logged. The fix logs them under an error id and returns only that id to the caller.\u003c/p\u003e\n\u003cp\u003eThis issue affects ash_ai: from 1.5.0 before 1.5.1.\u003c/p\u003e"
            },
            {
              "base64": false,
              "type": "text/markdown",
              "value": "Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail.\n\n`AshAi.ToToolError` gained an implementation for `Ash.Error.Unknown.UnknownError` that returns the error\u0027s `error` field as is, and `AshAi.Tool.Errors.format/1` sends that text to MCP clients (tool calls and resource reads in `AshAi.Mcp.Server`) and to the model in `AshAi.ToolLoop`. Ash stores the full `Exception.format/2` output of a raised exception, or `inspect/1` of a bare `{:error, term}` return, in that field. A tool result that cannot be JSON-encoded raises a `Protocol.UndefinedError` whose text includes the inspected value, which can be a whole record with fields the tool never returns. None of these errors were logged. The fix logs them under an error id and returns only that id to the caller.\n\nThis issue affects ash_ai: from 1.5.0 before 1.5.1."
            }
          ],
          "value": "Generation of Error Message Containing Sensitive Information vulnerability in ash-project ash_ai allows a caller of an AshAi tool to read internal error details, including module names and data values, by making a tool call fail.\n\nAshAi.ToToolError gained an implementation for Ash.Error.Unknown.UnknownError that returns the error\u0027s error field as is, and AshAi.Tool.Errors.format/1 sends that text to MCP clients (tool calls and resource reads in AshAi.Mcp.Server) and to the model in AshAi.ToolLoop. Ash stores the full Exception.format/2 output of a raised exception, or inspect/1 of a bare {:error, term} return, in that field. A tool result that cannot be JSON-encoded raises a Protocol.UndefinedError whose text includes the inspected value, which can be a whole record with fields the tool never returns. None of these errors were logged. The fix logs them under an error id and returns only that id to the caller.\n\nThis issue affects ash_ai: from 1.5.0 before 1.5.1."
        }
      ],
      "impacts": [
        {
          "capecId": "CAPEC-215",
          "descriptions": [
            {
              "lang": "en",
              "supportingMedia": [
                {
                  "base64": false,
                  "type": "text/html",
                  "value": "\u003cp\u003eA caller with tool access sends unexpected or malformed tool arguments until a tool fails, then reads the returned error text to learn internal module and function names and the values the code failed on.\u003c/p\u003e"
                },
                {
                  "base64": false,
                  "type": "text/markdown",
                  "value": "A caller with tool access sends unexpected or malformed tool arguments until a tool fails, then reads the returned error text to learn internal module and function names and the values the code failed on."
                }
              ],
              "value": "A caller with tool access sends unexpected or malformed tool arguments until a tool fails, then reads the returned error text to learn internal module and function names and the values the code failed on."
            }
          ]
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM",
            "privilegesRequired": "LOW",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:N/VA:N/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "NONE",
            "vulnConfidentialityImpact": "LOW",
            "vulnIntegrityImpact": "NONE",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-209",
              "description": "CWE-209 Generation of Error Message Containing Sensitive Information",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-11-09T13:03:21.386Z",
        "orgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
        "shortName": "EEF"
      },
      "references": [
        {
          "name": "Information disclosure in `AshAi.ToToolError` in AshAi sends raw exception text to tool callers",
          "tags": [
            "vendor-advisory",
            "related"
          ],
          "url": "https://github.com/ash-project/ash_ai/security/advisories/GHSA-vhmw-fwrr-r6c6"
        },
        {
          "name": "EEF CNA record for CVE-2026-119613",
          "tags": [
            "related"
          ],
          "url": "https://cna.erlef.org/cves/CVE-2026-119613.html"
        },
        {
          "name": "OSV record EEF-CVE-2026-119613",
          "tags": [
            "related"
          ],
          "url": "https://osv.dev/vulnerability/EEF-CVE-2026-119613"
        },
        {
          "name": "Introducing commit fbad04e in ash-project/ash_ai",
          "tags": [
            "related"
          ],
          "url": "https://github.com/ash-project/ash_ai/commit/fbad04e9620ef70603f4e67e03f15092f58578f6"
        },
        {
          "name": "Fix commit af79877 in ash-project/ash_ai",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/ash-project/ash_ai/commit/af7987769d78ed070c8a9f6e6ee542d91744eae6"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "title": "AshAi sends unrecognized tool errors verbatim to MCP clients and the model, disclosing internal details"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "6b3ad84c-e1a6-4bf7-a703-f496b71e49db",
    "assignerShortName": "EEF",
    "cveId": "CVE-2026-119613",
    "datePublished": "2026-11-09T13:03:21.386Z",
    "dateReserved": "2026-10-30T23:45:01.997Z",
    "dateUpdated": "2026-11-09T13:03:21.386Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.

Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

JSON
Events included in the timeline

Loading timeline…


    Loading…

    Loading…

    Loading…

    Related by attack behaviour

    Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.