CVE-2026-18489 (GCVE-0-2026-18489)
Vulnerability from cvelistv5 – Published: 2026-09-04 16:23 – Updated: 2026-09-04 17:29
VLAI
EPSS
VEX
Title
IBM ContextForge Translate is affected by cross-client credential context confusion
Summary
IBM ContextForge MCP Gateway - Translate utility <= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session.
Severity
7.4 (High)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-04 17:29 UTC
CWE
- CWE-488 - Exposure of Data Element to Wrong Session
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://www.ibm.com/support/pages/node/7286056 | vendor-advisorypatch |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| IBM | ContextForge MCP Gateway - Translate utility |
Affected:
<= 1.0.8
cpe:2.3:a:ibm:contextforge_mcp_gateway_translate_utility:*:*:*:*:*:*:*:* |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-18489",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-04T17:29:48.993058Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-04T17:29:57.267Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"cpes": [
"cpe:2.3:a:ibm:contextforge_mcp_gateway_translate_utility:*:*:*:*:*:*:*:*"
],
"product": "ContextForge MCP Gateway - Translate utility",
"vendor": "IBM",
"versions": [
{
"status": "affected",
"version": "\u003c= 1.0.8"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eIBM ContextForge MCP Gateway - Translate utility \u0026lt;= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session.\u003c/p\u003e"
}
],
"value": "IBM ContextForge MCP Gateway - Translate utility \u003c= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.4,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-488",
"description": "CWE-488 Exposure of Data Element to Wrong Session",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-04T16:23:08.905Z",
"orgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"shortName": "ibm"
},
"references": [
{
"tags": [
"vendor-advisory",
"patch"
],
"url": "https://www.ibm.com/support/pages/node/7286056"
}
],
"solutions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003cdiv\u003eIBM strongly recommends addressing the vulnerability now.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eThe IBM ContextForge Translate service is intended **only for local, single-session development use**. It does not provide the session isolation required for production or multi-client deployments. Users must ensure the Translate service is not exposed in any production capacity.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003ePR [#6388](\u003ca href=\"https://github.com/IBM/mcp-context-forge/pull/6388%29\" rel=\"nofollow\"\u003ehttps://github.com/IBM/mcp-context-forge/pull/6388)\u003c/a\u003e (merged 2026-08-24) updates the product documentation to make this restriction explicit, removing previous guidance that could have implied multi-tenant production suitability.\u003c/div\u003e\u003c/div\u003e"
}
],
"value": "IBM strongly recommends addressing the vulnerability now.\n\n\nThe IBM ContextForge Translate service is intended **only for local, single-session development use**. It does not provide the session isolation required for production or multi-client deployments. Users must ensure the Translate service is not exposed in any production capacity.\n\n\nPR [#6388]( https://github.com/IBM/mcp-context-forge/pull/6388) https://github.com/IBM/mcp-context-forge/pull/6388%29 (merged 2026-08-24) updates the product documentation to make this restriction explicit, removing previous guidance that could have implied multi-tenant production suitability."
}
],
"title": "IBM ContextForge Translate is affected by cross-client credential context confusion",
"workarounds": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003cdiv\u003eDo not use the IBM ContextForge Translate service in any production or multi-client environment. The service is designed exclusively for local development scenarios where only a single client session is expected. This applies regardless of whether `--enable-dynamic-env` is active.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eIf the Translate service is currently running in a non-development environment:\u003c/div\u003e\u003cdiv\u003e1. Stop the Translate service and remove it from any production deployment immediately.\u003c/div\u003e\u003cdiv\u003e2. Rotate any credentials (API tokens, `Authorization` headers) that may have been mapped into the shared subprocess environment while multiple clients were connected.\u003c/div\u003e\u003cdiv\u003e3. Review audit logs for tool calls where the HTTP caller identity may not match the subprocess credential context.\u003c/div\u003e\u003c/div\u003e"
}
],
"value": "Do not use the IBM ContextForge Translate service in any production or multi-client environment. The service is designed exclusively for local development scenarios where only a single client session is expected. This applies regardless of whether `--enable-dynamic-env` is active.\n\n\nIf the Translate service is currently running in a non-development environment:\n\n1. Stop the Translate service and remove it from any production deployment immediately.\n\n2. Rotate any credentials (API tokens, `Authorization` headers) that may have been mapped into the shared subprocess environment while multiple clients were connected.\n\n3. Review audit logs for tool calls where the HTTP caller identity may not match the subprocess credential context."
}
]
}
},
"cveMetadata": {
"assignerOrgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"assignerShortName": "ibm",
"cveId": "CVE-2026-18489",
"datePublished": "2026-09-04T16:23:08.905Z",
"dateReserved": "2026-07-31T13:49:30.524Z",
"dateUpdated": "2026-09-04T17:29:57.267Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-18489",
"date": "2026-11-07",
"epss": "0.00423",
"percentile": "0.36825"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"cpes": [
"cpe:2.3:a:ibm:contextforge_mcp_gateway_translate_utility:*:*:*:*:*:*:*:*"
],
"product": "ContextForge MCP Gateway - Translate utility",
"vendor": "IBM",
"versions": [
{
"status": "affected",
"version": "\u003c= 1.0.8"
}
]
}
],
"source": "psirt@us.ibm.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ibm:contextforge:*:*:*:*:*:python:*:*",
"matchCriteriaId": "7AF5E523-F344-4289-AE5E-1B1231CE6857",
"versionEndIncluding": "1.0.8",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "IBM ContextForge MCP Gateway - Translate utility \u003c= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session."
}
],
"id": "CVE-2026-18489",
"lastModified": "2026-09-15T15:04:09.813",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.4,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N",
"version": "3.1"
},
"exploitabilityScore": 2.2,
"impactScore": 5.2,
"source": "psirt@us.ibm.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-18489",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-04T17:29:48.993058Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-09-04T17:16:56.550",
"references": [
{
"source": "psirt@us.ibm.com",
"tags": [
"Patch",
"Vendor Advisory"
],
"url": "https://www.ibm.com/support/pages/node/7286056"
}
],
"sourceIdentifier": "psirt@us.ibm.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-488"
}
],
"source": "psirt@us.ibm.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-18489",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-04T17:29:48.993058Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-04T17:29:53.682Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"cpes": [
"cpe:2.3:a:ibm:contextforge_mcp_gateway_translate_utility:*:*:*:*:*:*:*:*"
],
"product": "ContextForge MCP Gateway - Translate utility",
"vendor": "IBM",
"versions": [
{
"status": "affected",
"version": "\u003c= 1.0.8"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eIBM ContextForge MCP Gateway - Translate utility \u0026lt;= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session.\u003c/p\u003e"
}
],
"value": "IBM ContextForge MCP Gateway - Translate utility \u003c= 1.0.8 MCP Context Forge could allow a remote attacker to obtain sensitive information from other sessions due to exposure of data elements to the wrong session."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.4,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-488",
"description": "CWE-488 Exposure of Data Element to Wrong Session",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-04T16:23:08.905Z",
"orgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"shortName": "ibm"
},
"references": [
{
"tags": [
"vendor-advisory",
"patch"
],
"url": "https://www.ibm.com/support/pages/node/7286056"
}
],
"solutions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003cdiv\u003eIBM strongly recommends addressing the vulnerability now.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eThe IBM ContextForge Translate service is intended **only for local, single-session development use**. It does not provide the session isolation required for production or multi-client deployments. Users must ensure the Translate service is not exposed in any production capacity.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003ePR [#6388](\u003ca href=\"https://github.com/IBM/mcp-context-forge/pull/6388%29\" rel=\"nofollow\"\u003ehttps://github.com/IBM/mcp-context-forge/pull/6388)\u003c/a\u003e (merged 2026-08-24) updates the product documentation to make this restriction explicit, removing previous guidance that could have implied multi-tenant production suitability.\u003c/div\u003e\u003c/div\u003e"
}
],
"value": "IBM strongly recommends addressing the vulnerability now.\n\n\nThe IBM ContextForge Translate service is intended **only for local, single-session development use**. It does not provide the session isolation required for production or multi-client deployments. Users must ensure the Translate service is not exposed in any production capacity.\n\n\nPR [#6388]( https://github.com/IBM/mcp-context-forge/pull/6388) https://github.com/IBM/mcp-context-forge/pull/6388%29 (merged 2026-08-24) updates the product documentation to make this restriction explicit, removing previous guidance that could have implied multi-tenant production suitability."
}
],
"title": "IBM ContextForge Translate is affected by cross-client credential context confusion",
"workarounds": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cdiv\u003e\u003cdiv\u003eDo not use the IBM ContextForge Translate service in any production or multi-client environment. The service is designed exclusively for local development scenarios where only a single client session is expected. This applies regardless of whether `--enable-dynamic-env` is active.\u003c/div\u003e\u003cbr/\u003e\u003cdiv\u003eIf the Translate service is currently running in a non-development environment:\u003c/div\u003e\u003cdiv\u003e1. Stop the Translate service and remove it from any production deployment immediately.\u003c/div\u003e\u003cdiv\u003e2. Rotate any credentials (API tokens, `Authorization` headers) that may have been mapped into the shared subprocess environment while multiple clients were connected.\u003c/div\u003e\u003cdiv\u003e3. Review audit logs for tool calls where the HTTP caller identity may not match the subprocess credential context.\u003c/div\u003e\u003c/div\u003e"
}
],
"value": "Do not use the IBM ContextForge Translate service in any production or multi-client environment. The service is designed exclusively for local development scenarios where only a single client session is expected. This applies regardless of whether `--enable-dynamic-env` is active.\n\n\nIf the Translate service is currently running in a non-development environment:\n\n1. Stop the Translate service and remove it from any production deployment immediately.\n\n2. Rotate any credentials (API tokens, `Authorization` headers) that may have been mapped into the shared subprocess environment while multiple clients were connected.\n\n3. Review audit logs for tool calls where the HTTP caller identity may not match the subprocess credential context."
}
]
}
},
"cveMetadata": {
"assignerOrgId": "9a959283-ebb5-44b6-b705-dcc2bbced522",
"assignerShortName": "ibm",
"cveId": "CVE-2026-18489",
"datePublished": "2026-09-04T16:23:08.905Z",
"dateReserved": "2026-07-31T13:49:30.524Z",
"dateUpdated": "2026-09-04T17:29:57.267Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
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.
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
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
How durations are calculated
Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.
Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.
Loading timeline…
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
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.