CWE-1427 Detalhe

CWE-1427

Improper Neutralization of Input Used for LLM Prompting
Incomplete
2024-11-19
00h00 +00:00
2025-12-11
00h00 +00:00
CWE Mitre.org
Notificações para um CWE
Fique informado sobre quaisquer alterações para um CWE específico.
Gerenciar notificações

Nome: Improper Neutralization of Input Used for LLM Prompting

The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives.

Informações Gerais

Modos de Introdução

Architecture and Design
Implementation
Implementation
System Configuration
Integration
Bundling

Plataformas Aplicáveis

Linguagem

Class: Not Language-Specific (Undetermined)

Sistemas Operacionais

Class: Not OS-Specific (Undetermined)

Arquiteturas

Class: Not Architecture-Specific (Undetermined)

Tecnologias

Name: AI/ML (Undetermined)

Consequências Comuns

Escopo Impacto Probabilidade
Confidentiality
Integrity
Availability		Execute Unauthorized Code or Commands, Varies by Context
ConfidentialityRead Application Data
IntegrityModify Application Data, Execute Unauthorized Code or Commands
Access ControlRead Application Data, Modify Application Data, Gain Privileges or Assume Identity

Exemplos Observados

Referências Descrição

CVE-2023-32786

Chain: LLM integration framework has prompt injection (CWE-1427) that allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF (CWE-918) and potentially injecting content into downstream tasks.

CVE-2024-5184

ML-based email analysis product uses an API service that allows a malicious user to inject a direct prompt and take over the service logic, forcing it to leak the standard hard-coded system prompts and/or execute unwanted prompts to leak sensitive data.

CVE-2024-5565

Chain: library for generating SQL via LLMs using RAG uses a prompt function to present the user with visualized results, allowing altering of the prompt using prompt injection (CWE-1427) to run arbitrary Python code (CWE-94) instead of the intended visualization code.

CVE-2024-48746

AI-based integration with business intel dashboard allows prompt injection through its natural language component, allowing execution of arbitrary code

Mitigações Potenciais

Phases : Architecture and Design
Phases : Implementation
Phases : Architecture and Design
Phases : Implementation
Phases : Installation // Operation
Phases : System Configuration

Métodos de Detecção

Dynamic Analysis with Manual Results Interpretation

Dynamic Analysis with Automated Results Interpretation

Architecture or Design Review

Notas de Mapeamento de Vulnerabilidade

Justificativa : This CWE entry is at the Base level of abstraction, which is a preferred level of abstraction for mapping to the root causes of vulnerabilities.
Comentário : Ensure that the weakness being identified involves improper neutralization during prompt generation. A different CWE might be needed if the core concern is related to inadvertent insertion of sensitive information, generating prompts from third-party sources that should not have been trusted (as may occur with indirect prompt injection), or jailbreaking, then the root cause might be a different weakness.

Referências

REF-1450

OWASP Top 10 for Large Language Model Applications - LLM01
OWASP.
https://genai.owasp.org/llmrisk/llm01-prompt-injection/

REF-1451

IBM - What is a prompt injection attack?
Matthew Kosinski, Amber Forrest.
https://www.ibm.com/think/topics/prompt-injection

REF-1452

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres, Thorsten Holz, Mario Fritz.
https://arxiv.org/abs/2302.12173

Submissão

Nome Organização Data Data de lançamento Version
Max Rattray Praetorian 2024-06-21 +00:00 2024-11-19 +00:00 4.16

Modificações

Nome Organização Data Comentário
CWE Content Team MITRE 2025-09-09 +00:00 updated References
CWE Content Team MITRE 2025-12-11 +00:00 updated Observed_Examples, Weakness_Ordinalities
As informações apresentadas no CVE Find originam-se de várias fontes de referência cuidadosamente selecionadas. Os dados CVE são fornecidos pela MITRE Corporation e pelo National Vulnerability Database (NVD). O catálogo de Vulnerabilidades Conhecidas Exploradas (KEV) é proveniente da Cybersecurity and Infrastructure Security Agency (CISA), enquanto as pontuações EPSS vêm do FIRST.org. Além disso, os dados sobre fraquezas de software (CWE) e padrões de ataque comuns (CAPEC) são mantidos pela MITRE Corporation, e as informações sobre configurações de hardware e software (CPE) são fornecidas pelo NVD.