Moderne licensed

OWASP LLM01 — Prompt Injection

Recipe IDorg.openrewrite.ai.security.OwaspLlm01Artifactorg.openrewrite.recipe:rewrite-java-security

OWASP LLM01 covers user or external input manipulating an LLM's behavior — overriding system prompts, exfiltrating data, or driving unsafe tool calls. This composite aggregates the individual detections that surface code shapes which let a prompt injection reach a model.

Composite recipeaiCWE-1427securityOWASP-LLM01OWASPProprietary

Usage

This recipe has no required configuration options. You’ll need the Moderne CLI configured before running the command below.

mod run . --recipe org.openrewrite.ai.security.OwaspLlm01

If the recipe isn’t available locally, install it with:

mod config recipes jar install org.openrewrite.recipe:rewrite-java-security:RELEASE

Definition

This recipe runs the following recipes in order.

Find prompt injection (OWASP LLM01)org.openrewrite.ai.security.FindPromptInjection
Find unguarded RAG content flowing into an LLM prompt (OWASP LLM01)org.openrewrite.ai.security.FindUnguardedRagInput
Find unrestricted prompt selection (OWASP LLM01)org.openrewrite.ai.security.FindUnrestrictedPromptSelection
Find LLM freeform output flowing into a structured parser (OWASP LLM01)org.openrewrite.ai.security.FindMissingStructuredOutput

Data tables

Structured output this recipe can produce.

Source files that had resultsSource files that were modified by the recipe run.org.openrewrite.table.SourcesFileResults
Source files that had search resultsSearch results that were found during the recipe run.org.openrewrite.table.SearchResults
Source files that errored on a recipeThe details of all errors produced by a recipe run.org.openrewrite.table.SourcesFileErrors
Recipe performanceStatistics used in analyzing the performance of recipes.org.openrewrite.table.RecipeRunStats