{"api_version":"1","generated_at":"2026-11-16T19:13:12+00:00","cve":"CVE-2026-119613","urls":{"html":"https://cve.report/CVE-2026-119613","api":"https://cve.report/api/cve/CVE-2026-119613.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-119613","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-119613"},"summary":{"title":"AshAi sends unrecognized tool errors verbatim to MCP clients and the model, disclosing internal details","description":"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'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.\n\nThis issue affects ash_ai: from 1.5.0 before 1.5.1.","state":"PUBLISHED","assigner":"EEF","published_at":"2026-11-09 13:17:06","updated_at":"2026-11-12 19:34:34"},"problem_types":["CWE-209","CWE-209 CWE-209 Generation of Error Message Containing Sensitive Information"],"metrics":[{"version":"4.0","source":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","type":"Secondary","score":"5.3","severity":"MEDIUM","vector":"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/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","data":{"version":"4.0","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/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","baseScore":5.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"LOW","userInteraction":"NONE","vulnConfidentialityImpact":"LOW","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"NONE","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}},{"version":"4.0","source":"CNA","type":"CVSS","score":"5.3","severity":"MEDIUM","vector":"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","data":{"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"}}],"references":[{"url":"https://github.com/ash-project/ash_ai/commit/af7987769d78ed070c8a9f6e6ee542d91744eae6","name":"https://github.com/ash-project/ash_ai/commit/af7987769d78ed070c8a9f6e6ee542d91744eae6","refsource":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/ash-project/ash_ai/security/advisories/GHSA-vhmw-fwrr-r6c6","name":"https://github.com/ash-project/ash_ai/security/advisories/GHSA-vhmw-fwrr-r6c6","refsource":"134c704f-9b21-4f2e-91b3-4a467353bcc0","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://github.com/ash-project/ash_ai/commit/fbad04e9620ef70603f4e67e03f15092f58578f6","name":"https://github.com/ash-project/ash_ai/commit/fbad04e9620ef70603f4e67e03f15092f58578f6","refsource":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://cna.erlef.org/cves/CVE-2026-119613.html","name":"https://cna.erlef.org/cves/CVE-2026-119613.html","refsource":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://osv.dev/vulnerability/EEF-CVE-2026-119613","name":"https://osv.dev/vulnerability/EEF-CVE-2026-119613","refsource":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-119613","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-119613","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"ash-project","product":"ash_ai","version":"affected 1.5.0 1.5.1 semver","platforms":[]},{"source":"CNA","vendor":"ash-project","product":"ash_ai","version":"affected fbad04e9620ef70603f4e67e03f15092f58578f6 af7987769d78ed070c8a9f6e6ee542d91744eae6 git","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[{"source":"CNA","value":"Sebastian Seilund","lang":"en"},{"source":"CNA","value":"Sebastian Seilund","lang":"en"},{"source":"CNA","value":"Zach Daniel / Ash Project","lang":"en"},{"source":"CNA","value":"Jonatan Männchen / EEF","lang":"en"}],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":{"cve_year":"2026","cve_id":"119613","cve":"CVE-2026-119613","epss":"0.002680000","percentile":"0.191430000","score_date":"2026-11-12","updated_at":"2026-11-13 00:14:35"},"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"adp":[{"metrics":[{"other":{"content":{"id":"CVE-2026-119613","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"partial"}],"role":"CISA Coordinator","timestamp":"2026-11-12T16:10:54.442769Z","version":"2.0.3"},"type":"ssvc"}}],"providerMetadata":{"dateUpdated":"2026-11-12T16:11:19.623Z","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","shortName":"CISA-ADP"},"references":[{"tags":["exploit"],"url":"https://github.com/ash-project/ash_ai/security/advisories/GHSA-vhmw-fwrr-r6c6"}],"title":"CISA ADP Vulnrichment"}],"cna":{"affected":[{"collectionURL":"https://repo.hex.pm","cpes":["cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:*"],"defaultStatus":"unaffected","modules":["'Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError'","'Elixir.AshAi.Tool.Errors'","'Elixir.AshAi.Mcp.Router'","'Elixir.AshAi.ToolLoop'"],"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":"'Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError':to_tool_error/1"},{"name":"'Elixir.AshAi.Tool.Errors':format/1"},{"name":"'Elixir.AshAi.Mcp.Router':call/2"},{"name":"'Elixir.AshAi.ToolLoop':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":["'Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError'","'Elixir.AshAi.Tool.Errors'","'Elixir.AshAi.Mcp.Router'","'Elixir.AshAi.ToolLoop'"],"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":"'Elixir.AshAi.ToToolError.Ash.Error.Unknown.UnknownError':to_tool_error/1"},{"name":"'Elixir.AshAi.Tool.Errors':format/1"},{"name":"'Elixir.AshAi.Mcp.Router':call/2"},{"name":"'Elixir.AshAi.ToolLoop':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 Männchen / EEF"}],"dateAssigned":"2026-11-07T21:44:36.000Z","descriptions":[{"lang":"en","supportingMedia":[{"base64":false,"type":"text/html","value":"<p>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.</p>\n<p><code>AshAi.ToToolError</code> gained an implementation for <code>Ash.Error.Unknown.UnknownError</code> that returns the error's <code>error</code> field as is, and <code>AshAi.Tool.Errors.format/1</code> sends that text to MCP clients (tool calls and resource reads in <code>AshAi.Mcp.Server</code>) and to the model in <code>AshAi.ToolLoop</code>. Ash stores the full <code>Exception.format/2</code> output of a raised exception, or <code>inspect/1</code> of a bare <code>{:error, term}</code> return, in that field. A tool result that cannot be JSON-encoded raises a <code>Protocol.UndefinedError</code> 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.</p>\n<p>This issue affects ash_ai: from 1.5.0 before 1.5.1.</p>"},{"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'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.\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'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.\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":"<p>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.</p>"},{"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":"2026-11-12T16:11:19.623Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-11-09 13:17:06","lastModifiedDate":"2026-11-12 19:34:34","problem_types":["CWE-209","CWE-209 CWE-209 Generation of Error Message Containing Sensitive Information"],"metrics":{"cvssMetricV40":[{"source":"6b3ad84c-e1a6-4bf7-a703-f496b71e49db","type":"Secondary","cvssData":{"version":"4.0","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/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","baseScore":5.3,"baseSeverity":"MEDIUM","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"LOW","userInteraction":"NONE","vulnConfidentialityImpact":"LOW","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"NONE","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}}],"ssvcV203":[{"source":"134c704f-9b21-4f2e-91b3-4a467353bcc0","ssvcData":{"timestamp":"2026-11-12T16:10:54.442769Z","id":"CVE-2026-119613","options":[{"exploitation":"poc"},{"automatable":"no"},{"technicalImpact":"partial"}],"role":"CISA Coordinator","version":"2.0.3"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"119613","Ordinal":"1","Title":"AshAi sends unrecognized tool errors verbatim to MCP clients and","CVE":"CVE-2026-119613","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"119613","Ordinal":"1","NoteData":"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'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.\n\nThis issue affects ash_ai: from 1.5.0 before 1.5.1.","Type":"Description","Title":"AshAi sends unrecognized tool errors verbatim to MCP clients and"}]}}}