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.

What CVEs are caused by CWE-1427?

15 recorded CVEs are attributed to CWE-1427, including CVE-2026-44717, CVE-2026-78379, CVE-2026-4399.

How do you prevent CWE-1427?

LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included. Additionally, they should be designed in a way that ensures that user-controllable input is identified as untrusted and potentially dangerous.

How is CWE-1427 detected?

Dynamic Analysis with Manual Results Interpretation: Use known techniques for prompt injection and other attacks, and adjust the attacks to be more specific to the model or system.

What are the consequences of CWE-1427?

Exploiting CWE-1427 can lead to: Execute Unauthorized Code or Commands, Varies by Context, Read Application Data, Modify Application Data, Gain Privileges or Assume Identity.

Is CWE-1427 actively exploited?

15 recorded CVEs are caused by CWE-1427; none are currently in CISA's KEV catalog of actively exploited flaws.

CWE-1427: Improper Neutralization of Input Used for LLM Prompting (prompt injection)

RadicalNotion.AI

Code examples

Illustrative examples from MITRE showing how the weakness appears in code.

Consider a "CWE Differentiator" application that uses an an LLM generative AI based "chatbot" to explain the difference between two weaknesses. As input, it accepts two CWE IDs, constructs a prompt string, sends the prompt to the chatbot, and prints the results. The prompt string effectively acts as a command to the chatbot component. Assume that invokeChatbot() calls the chatbot and returns the response as a string; the implementation details are not important here.

Vulnerable example

python

prompt = "Explain the difference between {} and {}".format(arg1, arg2)

Example

plaintext

Explain the difference between CWE-77 and CWE-78

Attack input

plaintext

Arg1 = CWE-77

Resulting query

plaintext

Explain the difference between CWE-77 and CWE-78.

Safe example

python

cweRegex = re.compile("^CWE-\d+$")

Consider this code for an LLM agent that tells a joke based on user-supplied content. It uses LangChain to interact with OpenAI.

CWE-1427: Improper Neutralization of Input Used for LLM Prompting

Overview

Real-world CVEs

Common consequences

How it happens

When it is introduced

Applies to

How to prevent it

How to detect it

Dynamic Analysis with Manual Results Interpretation

Dynamic Analysis with Automated Results Interpretation

Architecture or Design Review

Code examples

Illustrative examples

Terminology & mappings

Alternate terms

Frequently asked questions

References

Stay ahead of CWE-1427

Overview

Real-world CVEs

Common consequences

How it happens

When it is introduced

Applies to

How to prevent it

How to detect it

Dynamic Analysis with Manual Results Interpretation

Dynamic Analysis with Automated Results Interpretation

Architecture or Design Review

Code examples

Illustrative examples

Related weaknesses

Parent

Terminology & mappings

Alternate terms

Frequently asked questions

References

Stay ahead of CWE-1427