CVE-2026-33324 (GCVE-0-2026-33324)
Vulnerability from cvelistv5
Published
2026-05-05 19:09
Modified
2026-05-05 19:38
Severity ?
VLAI Severity ?
EPSS score ?
CWE
- CWE-89 - Improper Neutralization of Special Elements used in an SQL Command ('SQL Injection')
Summary
SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and the SQL extracted from the LLM response is executed against the database without validation or sanitization. An authenticated attacker can craft a malicious question to manipulate the LLM into generating and executing arbitrary SQL statements. When connected to a PostgreSQL data source, this can lead to remote code execution via COPY FROM PROGRAM. This issue has been fixed in version 1.7.1.
References
| URL | Tags | ||||
|---|---|---|---|---|---|
|
|||||
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-33324",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-05-05T19:38:13.639336Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-05-05T19:38:28.127Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "SQLBot",
"vendor": "dataease",
"versions": [
{
"status": "affected",
"version": "\u003c 1.7.1"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and the SQL extracted from the LLM response is executed against the database without validation or sanitization. An authenticated attacker can craft a malicious question to manipulate the LLM into generating and executing arbitrary SQL statements. When connected to a PostgreSQL data source, this can lead to remote code execution via COPY FROM PROGRAM. This issue has been fixed in version 1.7.1."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.4,
"baseSeverity": "CRITICAL",
"privilegesRequired": "LOW",
"subAvailabilityImpact": "HIGH",
"subConfidentialityImpact": "HIGH",
"subIntegrityImpact": "HIGH",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-89",
"description": "CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-05-05T19:09:36.031Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx"
}
],
"source": {
"advisory": "GHSA-q2q6-gqqh-4xrx",
"discovery": "UNKNOWN"
},
"title": "SQLBot prompt injection allows arbitrary SQL execution and remote code execution"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-33324",
"datePublished": "2026-05-05T19:09:36.031Z",
"dateReserved": "2026-03-18T21:23:36.677Z",
"dateUpdated": "2026-05-05T19:38:28.127Z",
"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-2026-33324\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-05T19:38:13.639336Z\"}}}], \"references\": [{\"url\": \"https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-05T19:38:24.072Z\"}}], \"cna\": {\"title\": \"SQLBot prompt injection allows arbitrary SQL execution and remote code execution\", \"source\": {\"advisory\": \"GHSA-q2q6-gqqh-4xrx\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 9.4, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"LOW\", \"subIntegrityImpact\": \"HIGH\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"HIGH\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"HIGH\", \"vulnConfidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"dataease\", \"product\": \"SQLBot\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.7.1\"}]}], \"references\": [{\"url\": \"https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx\", \"name\": \"https://github.com/dataease/SQLBot/security/advisories/GHSA-q2q6-gqqh-4xrx\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"SQLBot is an intelligent Text-to-SQL system based on large language models and RAG. In versions 1.7.0 and earlier, the Text2SQL chat interface is vulnerable to prompt injection. The user-provided question parameter is directly concatenated into the LLM prompt without filtering or escaping, and the SQL extracted from the LLM response is executed against the database without validation or sanitization. An authenticated attacker can craft a malicious question to manipulate the LLM into generating and executing arbitrary SQL statements. When connected to a PostgreSQL data source, this can lead to remote code execution via COPY FROM PROGRAM. This issue has been fixed in version 1.7.1.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-89\", \"description\": \"CWE-89: Improper Neutralization of Special Elements used in an SQL Command (\u0027SQL Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-05T19:09:36.031Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-33324\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-05-05T19:38:28.127Z\", \"dateReserved\": \"2026-03-18T21:23:36.677Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-05-05T19:09:36.031Z\", \"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…