{"dataType": "CVE_RECORD", "dataVersion": "5.1", "cveMetadata": {"cveId": "CVE-2024-7764", "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "state": "PUBLISHED", "assignerShortName": "@huntr_ai", "dateReserved": "2024-08-13T18:24:14.074Z", "datePublished": "2025-03-20T10:11:35.662Z", "dateUpdated": "2025-03-20T13:43:43.656Z"}, "containers": {"cna": {"title": "SQL Injection in vanna-ai/vanna", "providerMetadata": {"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "shortName": "@huntr_ai", "dateUpdated": "2025-03-20T10:11:35.662Z"}, "descriptions": [{"lang": "en", "value": "Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker's command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema."}], "affected": [{"vendor": "vanna-ai", "product": "vanna-ai/vanna", "versions": [{"version": "unspecified", "status": "affected", "versionType": "custom", "lessThanOrEqual": "latest"}]}], "references": [{"url": "https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f"}], "metrics": [{"cvssV3_0": {"version": "3.0", "attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "NONE", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N", "baseScore": 8.1, "baseSeverity": "HIGH"}}], "problemTypes": [{"descriptions": [{"type": "CWE", "lang": "en", "description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command", "cweId": "CWE-89"}]}], "source": {"advisory": "85d403b1-fbed-42e9-9ec1-2f79abf6eb0f", "discovery": "EXTERNAL"}}, "adp": [{"metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2025-03-20T13:43:19.044296Z", "id": "CVE-2024-7764", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-03-20T13:43:43.656Z"}}]}}

{"dataType": "CVE_RECORD", "containers": {"adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2024-7764", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2025-03-20T13:43:19.044296Z"}}}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2025-03-20T13:43:40.306Z"}}], "cna": {"title": "SQL Injection in vanna-ai/vanna", "source": {"advisory": "85d403b1-fbed-42e9-9ec1-2f79abf6eb0f", "discovery": "EXTERNAL"}, "metrics": [{"cvssV3_0": {"scope": "UNCHANGED", "version": "3.0", "baseScore": 8.1, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}}], "affected": [{"vendor": "vanna-ai", "product": "vanna-ai/vanna", "versions": [{"status": "affected", "version": "unspecified", "versionType": "custom", "lessThanOrEqual": "latest"}]}], "references": [{"url": "https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f"}], "descriptions": [{"lang": "en", "value": "Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker's command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema."}], "problemTypes": [{"descriptions": [{"lang": "en", "type": "CWE", "cweId": "CWE-89", "description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command"}]}], "providerMetadata": {"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "shortName": "@huntr_ai", "dateUpdated": "2025-03-20T10:11:35.662Z"}}}, "cveMetadata": {"cveId": "CVE-2024-7764", "state": "PUBLISHED", "dateUpdated": "2025-03-20T13:43:43.656Z", "dateReserved": "2024-08-13T18:24:14.074Z", "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "datePublished": "2025-03-20T10:11:35.662Z", "assignerShortName": "@huntr_ai"}, "dataVersion": "5.1"}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker's command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema."}, {"lang": "es", "value": "Vanna-ai v0.6.2 es vulnerable a la inyecci\u00f3n de SQL debido a la protecci\u00f3n insuficiente contra la inyecci\u00f3n de comandos SQL adicionales provenientes de las solicitudes de usuario. La vulnerabilidad se produce cuando la funci\u00f3n `generate_sql` llama a `extract_sql` con la respuesta LLM. Un atacante puede incluir un punto y coma entre un campo de datos de b\u00fasqueda y su propio comando, lo que provoca que la funci\u00f3n `extract_sql` elimine todo el SQL generado por LLM y ejecute el comando del atacante si este pasa la funci\u00f3n `is_sql_valid`. Esto permite la ejecuci\u00f3n de SQL definido por el usuario m\u00e1s all\u00e1 de los l\u00edmites previstos, en particular del esquema entrenado."}], "id": "CVE-2024-7764", "lastModified": "2026-04-15T00:35:42.020", "metrics": {"cvssMetricV30": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "NONE", "baseScore": 8.1, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "LOW", "scope": "UNCHANGED", "userInteraction": "NONE", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N", "version": "3.0"}, "exploitabilityScore": 2.8, "impactScore": 5.2, "source": "security@huntr.dev", "type": "Secondary"}]}, "published": "2025-03-20T10:15:36.717", "references": [{"source": "security@huntr.dev", "url": "https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f"}], "sourceIdentifier": "security@huntr.dev", "vulnStatus": "Deferred", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-89"}], "source": "security@huntr.dev", "type": "Secondary"}]}

{}

{"created": "2025-07-12T22:23:29.815880+00:00", "updated": "2025-07-12T22:23:29.815929+00:00", "vendors": ["vanna-ai", "vanna-ai$PRODUCT$vanna"]}