名稱: 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.

一般資訊

引入方式

Architecture and Design
Implementation
Implementation
System Configuration
Integration
Bundling

適用平台

程式語言

類別： Not Language-Specific (Undetermined)

作業系統

類別： Not OS-Specific (Undetermined)

架構

類別： Not Architecture-Specific (Undetermined)

技術

名稱： AI/ML (Undetermined)

常見後果

範圍	影響	可能性
Confidentiality Integrity Availability	Execute Unauthorized Code or Commands, Varies by Context
Confidentiality	Read Application Data
Integrity	Modify Application Data, Execute Unauthorized Code or Commands
Access Control	Read Application Data, Modify Application Data, Gain Privileges or Assume Identity

觀察到的案例

參考資料	描述
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

潛在緩解措施

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

偵測方法

Dynamic Analysis with Manual Results Interpretation

Dynamic Analysis with Automated Results Interpretation

Architecture or Design Review

漏洞對應備注

理由說明 : 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.
備註 : 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.

參考資料

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

提交

名稱	機構	日期	發布日期	Version
Max Rattray	Praetorian	2024-06-21 +00:00	2024-11-19 +00:00	4.16

修改記錄

名稱	機構	日期	備註
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
CWE Content Team	MITRE	2026-04-30 +00:00	updated Relationships
CWE Content Team	MITRE	2026-10-28 +00:00	updated Demonstrative_Examples

CWE-1427 詳細資料

CWE-1427