Find unrestricted prompt selection (OWASP LLM01)
org.openrewrite.ai.security.FindUnrestrictedPromptSelectionArtifactorg.openrewrite.recipe:rewrite-java-securityFind code where untrusted input picks which LLM prompt template runs. Concretely, an HTTP request value — a servlet or Spring WebRequest accessor, or a Spring MVC handler parameter bound with @RequestParam, @PathVariable, @RequestHeader, @RequestBody, @RequestPart, @CookieValue, or @MatrixVariable — flows into a Map.get(...) key argument, and the value returned by that map lookup flows into an LLM prompt sink. This is the OWASP LLM01 shape where an attacker can jailbreak or escalate by switching to a system prompt they shouldn't be able to reach (tenant-prompt escape, admin templates, etc.). Taint tracking follows both legs of the flow through user-defined transformations.
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.FindUnrestrictedPromptSelectionIf the recipe isn’t available locally, install it with:
mod config recipes jar install org.openrewrite.recipe:rewrite-java-security:RELEASEData 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