CVE-2026-55071 (GCVE-0-2026-55071)
Vulnerability from cvelistv5
Published
2026-09-21 14:09
Modified
2026-09-21 14:56
Severity ?
VLAI Severity ?
EPSS score ?
CWE
- CWE-94 - Improper Control of Generation of Code ('Code Injection')
Summary
MCP-for-Stata is a MCP server for integrating Stata into agent loops with a safety-first design. Prior to version 1.19.0, the ado_package_install MCP tool in stata-mcp concatenates user-controlled input directly into a Stata command string without any validation or sanitization. An attacker who can invoke the MCP tool or the equivalent Python API can embed newline characters in the package argument to inject arbitrary Stata commands. Because Stata supports a shell escape command, this leads to full OS-level arbitrary command execution (RCE) under the account running the Stata-MCP server. The tool is registered in the default all profile, so no non-default configuration is required. This issue has been patched in version 1.19.0.
References
| URL | Tags | |||||||
|---|---|---|---|---|---|---|---|---|
|
||||||||
Impacted products
| Vendor | Product | Version | ||
|---|---|---|---|---|
| SepineTam | mcp-for-stata |
Version: < 1.19.0 |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-55071",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-21T14:56:21.699731Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-21T14:56:37.752Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "mcp-for-stata",
"vendor": "SepineTam",
"versions": [
{
"status": "affected",
"version": "\u003c 1.19.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "MCP-for-Stata is a MCP server for integrating Stata into agent loops with a safety-first design. Prior to version 1.19.0, the ado_package_install MCP tool in stata-mcp concatenates user-controlled input directly into a Stata command string without any validation or sanitization. An attacker who can invoke the MCP tool or the equivalent Python API can embed newline characters in the package argument to inject arbitrary Stata commands. Because Stata supports a shell escape command, this leads to full OS-level arbitrary command execution (RCE) under the account running the Stata-MCP server. The tool is registered in the default all profile, so no non-default configuration is required. This issue has been patched in version 1.19.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 8.4,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-94",
"description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-21T14:09:30.169Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9"
},
{
"name": "https://github.com/SepineTam/mcp-for-stata/releases/tag/v1.19.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/SepineTam/mcp-for-stata/releases/tag/v1.19.0"
}
],
"source": {
"advisory": "GHSA-49m4-vp58-wgc9",
"discovery": "UNKNOWN"
},
"title": "MCP-for-Stata: Stata Command Injection via Unsanitized `package` in `ado_package_install`"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-55071",
"datePublished": "2026-09-21T14:09:30.169Z",
"dateReserved": "2026-06-16T14:33:35.710Z",
"dateUpdated": "2026-09-21T14:56:37.752Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-55071\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-21T14:56:21.699731Z\"}}}], \"references\": [{\"url\": \"https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-21T14:56:31.832Z\"}}], \"cna\": {\"title\": \"MCP-for-Stata: Stata Command Injection via Unsanitized `package` in `ado_package_install`\", \"source\": {\"advisory\": \"GHSA-49m4-vp58-wgc9\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.4, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"SepineTam\", \"product\": \"mcp-for-stata\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.19.0\"}]}], \"references\": [{\"url\": \"https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9\", \"name\": \"https://github.com/SepineTam/mcp-for-stata/security/advisories/GHSA-49m4-vp58-wgc9\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/SepineTam/mcp-for-stata/releases/tag/v1.19.0\", \"name\": \"https://github.com/SepineTam/mcp-for-stata/releases/tag/v1.19.0\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"MCP-for-Stata is a MCP server for integrating Stata into agent loops with a safety-first design. Prior to version 1.19.0, the ado_package_install MCP tool in stata-mcp concatenates user-controlled input directly into a Stata command string without any validation or sanitization. An attacker who can invoke the MCP tool or the equivalent Python API can embed newline characters in the package argument to inject arbitrary Stata commands. Because Stata supports a shell escape command, this leads to full OS-level arbitrary command execution (RCE) under the account running the Stata-MCP server. The tool is registered in the default all profile, so no non-default configuration is required. This issue has been patched in version 1.19.0.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-09-21T14:09:30.169Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-55071\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-09-21T14:56:37.752Z\", \"dateReserved\": \"2026-06-16T14:33:35.710Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-09-21T14:09:30.169Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.
Loading…
Loading…