Skip to main content

Llamaindex CVE-2024-58339

HIGH
Allocation of Resources Without Limits or Throttling (CWE-770)
2026-01-12 disclosure@vulncheck.com
8.7
CVSS 4.0 · Vendor: vulncheck
View

Vulnerability Assessment

Weakness
CWE
OWASP Top 10:2025
A06:2025 - Insecure Design
ASVS 5.0
V2 - Validation and Business Logic Resource allocation limits
MITRE ATT&CK

1 technique across 1 tactic: Impact

The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up.

This Week Schedule remediation this week. Why: HIGH severity (CVSS 7.0-8.9).
Patch available 0.1% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv2 – Jul 14, 2026

Denial-of-service in LlamaIndex (run-llama/llama_index) versions up to and including 0.12.2 lets remote unauthenticated attackers exhaust CPU and memory through the VannaPack VannaQueryEngine. The engine's custom_query() converts a user-supplied natural-language prompt into SQL and runs it via vn.run_sql() with no execution limits, so a crafted prompt can produce an unbounded or extremely expensive query. Publicly available exploit code exists (Huntr bounty report), though EPSS is low at 0.12% (30th percentile) and it is not listed in CISA KEV.

Earlier versions of this analysis (1)
v1 Mar 12, 2026 - 21:54 CVSS 7.5

LlamaIndex (run-llama/llama_index) versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation. [CVSS 7.5 HIGH]

Affected Packages

pypi llama-index fix: 0.12.3

Source: OSV (Open Source Vulnerabilities)

Affects your stack

Affects 1 package in pypi

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Know when Llamaindex gets its next vulnerability

  • Watch products and get an email when something new is published
  • Check this CVE against your own stack and servers
  • Exploit and PoC references, threat intelligence from 22 sources

No credit card · 7-day full trial

Severity by source

Vendor (vulncheck) PRIMARY 8.7 HIGH
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (vulncheck) · only source for this CVE.

CVSS VectorVendor: vulncheck

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vulnerable system: Confidentiality
None
Vulnerable system: Integrity
None
Vulnerable system: Availability
High
Subsequent system: Confidentiality
None
Subsequent system: Integrity
None
Subsequent system: Availability
None

Lifecycle Timeline

4
Analysis Updated
Jul 14, 2026 - 23:29 vuln.today
v2 - CVSS changed
CVSS changed
Jul 14, 2026 - 23:22 NVD
7.5 (HIGH) 8.7 (HIGH)
PoC Detected
Jan 21, 2026 - 18:30 vuln.today
Public exploit code
CVE Published
Jan 12, 2026 - 23:15 nvd
HIGH 7.5

DescriptionCVE.org

LlamaIndex (run-llama/llama_index) versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation. The custom_query() logic generates SQL statements from a user-supplied prompt and executes them via vn.run_sql() without enforcing query execution limits In downstream deployments where untrusted users can supply prompts, an attacker can trigger expensive or unbounded SQL operations that exhaust CPU or memory resources, resulting in a denial-of-service condition. The vulnerable execution path occurs in llama_index/packs/vanna/base.py within custom_query().

Executive ViewAI

Why It Matters

LlamaIndex (v0.12.2 and earlier) contains a denial-of-service vulnerability exploitable by unauthenticated actors via the VannaPack query engine, which could crash or significantly degrade AI and data-access applications built on this framework. Any organization relying on LlamaIndex for natural-language database interaction faces potential service outages and should prioritize patching.

Recommended Action

Within 24 hours, inventory all internal applications using LlamaIndex and identify those with VannaPack VannaQueryEngine enabled; notify affected teams that publicly available exploit code exists. Within 7 days, apply the vendor-released patch to upgrade LlamaIndex beyond version 0.12.2 across all affected instances and validate functionality in staging. Within 30 days, conduct a full audit of LlamaIndex deployments to ensure all instances are patched and implement monitoring for abnormal resource consumption on patched systems.

Business Impact: High
Compensating Controls

Apply vendor patch.

Threat Intelligence Overview

EPSS Score
0.1%
Top 70% exploitable
Exploit
POC
Public exploit code exists
Data Quality
4 sources
Confidence: Medium

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue
Severity HIGH
CISA KEV No
Public POC Yes
EPSS 0.1%
Patch available Yes
Active threat No
Deciding rule
HIGH severity (CVSS 7.0-8.9)
What every action level means
Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.
Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.
This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.
This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.
Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived
Out-of-Cycle
Exploitation· derived
Poc
System Exposure· derived
Open
Automatable· derived
Yes
Human Impact
High

Priority Score

64
Low Medium High Critical
KEV: 0
EPSS: 0
CVSS: +44
PoC: +20
Weaponized: 0
Threat intel: 0
Gov advisory: 0

Attack Technique

Denial of Service attacks render applications or systems unavailable by overwhelming resources or triggering failure conditions.

Affected Products (CPE)CVE.org

cpe:2.3:a:llamaindex:llamaindex:*:*:*:*:*:*:*:*
CVE-2024-11958 CRITICAL POC
9.8 Mar 20

A SQL injection vulnerability exists in the `duckdb_retriever` component of the run-llama/llama_index repository, specif

CVE-2024-12909 CRITICAL POC
9.8 Mar 20

A vulnerability in the FinanceChatLlamaPack of the run-llama/llama_index repository, versions up to v0.12.3, allows for

CVE-2025-1750 CRITICAL POC
9.8 Jun 02

SQL injection in llama_index DuckDB vector store v0.12.19. PoC and patch available.

CVE-2025-1793 CRITICAL POC
9.8 Jun 05

Critical SQL injection vulnerability affecting run-llama/llama_index v0.12.21 and potentially other versions, present in

CVE-2024-3271 CRITICAL POC
9.8 Apr 16

A command injection vulnerability exists in the run-llama/llama_index repository, specifically within the safe_eval func

CVE-2024-23751 CRITICAL POC
9.8 Jan 22

LlamaIndex (aka llama_index) through 0.9.34 allows SQL injection via the Text-to-SQL feature in NLSQLTableQueryEngine, S

CVE-2023-39662 CRITICAL POC
9.8 Aug 15

An issue in llama_index v.0.7.13 and before allows a remote attacker to execute arbitrary code via the `exec` parameter

CVE-2024-4181 HIGH POC
8.8 May 16

A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the

CVE-2024-14021 HIGH POC
8.4 Jan 12

Arbitrary code execution in LlamaIndex (run-llama/llama_index) versions up to and including 0.11.6 occurs when BGEM3Inde

CVE-2025-7707 HIGH POC
7.8 Oct 13

Local privilege escalation and denial of service in llama_index 0.12.33 arising from its default configuration of a worl

CVE-2025-3108 HIGH POC
7.5 Jul 06

A critical deserialization vulnerability exists in the run-llama/llama_index library's JsonPickleSerializer component, a

CVE-2025-1752 HIGH POC
7.5 May 10

A Denial of Service (DoS) vulnerability has been identified in the KnowledgeBaseWebReader class of the run-llama/llama_i

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy