Security Digest · Vulnerability record
CVE-2024-23751: SQL injection in llama-index
LlamaIndex (aka llamaindex) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine.
CVSS 9.8 Critical EPSS 0.7% · p51
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.7%, percentile 51: FIRST’s model estimates a 0.7% chance of exploitation activity in the next 30 days, higher than 51% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
llama-index(PyPI) <= 0.9.35, no fixed version listed. Check your lockfile, including transitive dependencies.
What it is
LlamaIndex (aka llamaindex) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine. For example, an attacker might be able to delete this year's student records via "Drop the Students table" within English language input.
From the GitHub advisory
LlamaIndex (aka llamaindex) through 0.9.35 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, NLSQLRetriever, RetrieverQueryEngine, and PGVectorSQLQueryEngine. For example, an attacker might be able to delete this year's student records via "Drop the Students table" within English language input.
Weakness type: CWE-89.
Product: llama-index (PyPI) · Assigned by: mitre · Published: 2024-01-22
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | llama-index | <= 0.9.35 | none listed |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| n/a | n/a | see vendor advisory |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| CISA-ADP | 3.1 | 9.8 Critical | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact partial.
- FIRST EPSS (model of 2026-10-21): 0.66% probability of exploitation activity in the next 30 days; percentile 51.
Timeline
- — CVE record published by mitre
- — GitHub-reviewed advisory GHSA-2jxw-4hm4-6w87 published (critical)
- — CVE record last updated
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-2jxw-4hm4-6w87 github.com
- CVE.org record CVE-2024-23751 cve.org
- NVD entry CVE-2024-23751 nvd.nist.gov
Other references from the CVE record and advisory
- github.com github.com
- github.com github.com