CVE-2026-54140 (GCVE-0-2026-54140)
Vulnerability from cvelistv5 – Published: 2026-11-05 16:13 – Updated: 2026-11-09 17:19
VLAI
EPSS
VEX
Title
OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization
Summary
OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13.
Severity
8.3 (High)
SSVC
Exploitation: poc
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-11-09 17:18 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/tinyhumansai/openhuman/securit… | x_refsource_CONFIRM |
| https://github.com/tinyhumansai/openhuman/pull/3215 | x_refsource_MISC |
| https://github.com/tinyhumansai/openhuman/commit/… | x_refsource_MISC |
| https://github.com/tinyhumansai/openhuman/release… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | |
|---|---|---|---|
| tinyhumansai | openhuman |
Affected:
< 0.57.13
|
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-54140",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T17:18:30.482758Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-09T17:19:01.138Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "openhuman",
"vendor": "tinyhumansai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.57.13"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-1427",
"description": "CWE-1427:",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-05T16:13:31.126Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
},
{
"name": "https://github.com/tinyhumansai/openhuman/pull/3215",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/pull/3215"
},
{
"name": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e"
},
{
"name": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13"
}
],
"source": {
"advisory": "GHSA-g6j9-89xv-v752",
"discovery": "UNKNOWN"
},
"title": "OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-54140",
"datePublished": "2026-11-05T16:13:31.126Z",
"dateReserved": "2026-06-11T21:15:33.870Z",
"dateUpdated": "2026-11-09T17:19:01.138Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-54140",
"date": "2026-11-17",
"epss": "0.00554",
"percentile": "0.46844"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "openhuman",
"vendor": "tinyhumansai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.57.13"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13."
}
],
"id": "CVE-2026-54140",
"lastModified": "2026-11-09T18:17:29.263",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 1.6,
"impactScore": 6.0,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-54140",
"options": [
{
"exploitation": "poc"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T17:18:30.482758Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-11-05T17:18:18.910",
"references": [
{
"source": "security-advisories@github.com",
"url": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/tinyhumansai/openhuman/pull/3215"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
},
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Deferred"
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-54140",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-11-09T17:18:30.482758Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-11-09T17:18:42.785Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "openhuman",
"vendor": "tinyhumansai",
"versions": [
{
"status": "affected",
"version": "\u003c 0.57.13"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 8.3,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-1427",
"description": "CWE-1427:",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-11-05T16:13:31.126Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/tinyhumansai/openhuman/security/advisories/GHSA-g6j9-89xv-v752"
},
{
"name": "https://github.com/tinyhumansai/openhuman/pull/3215",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/pull/3215"
},
{
"name": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/commit/00b8a669c6e6391a1be9f724bd9c8f755ee3c43e"
},
{
"name": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/tinyhumansai/openhuman/releases/tag/v0.57.13"
}
],
"source": {
"advisory": "GHSA-g6j9-89xv-v752",
"discovery": "UNKNOWN"
},
"title": "OpenHuman: MCP tool description injection: untrusted server descriptions execute in agent LLM context without sanitization"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-54140",
"datePublished": "2026-11-05T16:13:31.126Z",
"dateReserved": "2026-06-11T21:15:33.870Z",
"dateUpdated": "2026-11-09T17:19:01.138Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
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.
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.
Loading…