Improper Neutralization of Input Used for LLM Prompting

Properties

id: d3f:CWE-1427

name
Improper Neutralization of Input Used for LLM Prompting
definition
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.
synonyms
prompt injection
json

Neighbors

CWE-1427 has no direct neighbors in this release.

Inferred Relationships

This page is experimental and may change significantly in future releases.

Related Countermeasure Techniques

No related defensive techniques in this release.

Related Weaknesses

Related Offensive Techniques

No related offensive techniques in this release.