Package: llmshieldr Title: Safety Guardrails for Large Language Model Workflows Version: 0.1.0 Description: A model-agnostic safety layer for developers building with large language model (LLM) applications. Maps starter controls to the Open Worldwide Application Security Project Top 10 for Large Language Model Applications 2025 risk categories via a modular rule engine. Supports regular-expression rules, lightweight natural language processing (NLP) intent checks, optional scanners, and semantic large language model reviewer checks on prompts, conversations, retrieved context, tool inputs and outputs, streaming chunks, and model outputs. Supports workflows with the 'Ollama' local web service via 'ellmer', remote reviewer endpoints, and other chat interfaces callable from 'R'. Intended as an experimental guardrail layer that teams should evaluate against their own workflows before relying on it in production. Authors@R: person("Indraneel", "Chakraborty", , "hello.indraneel@gmail.com", role = c("aut", "cre", "cph"), comment = c(ORCID = "0000-0001-6958-8269")) License: Apache License (>= 2) Encoding: UTF-8 Depends: R (>= 4.1.0) Imports: jsonlite, cli, rlang, digest, stringi Suggests: ellmer, httr2, processx, filelock, htmltools, covr, lintr, plumber, shiny, testthat (>= 3.0.0), knitr, rmarkdown, withr, dplyr, tokenizers, SnowballC Roxygen: list(markdown = TRUE) RoxygenNote: 7.3.3 VignetteBuilder: knitr Config/testthat/edition: 3 URL: https://www.indraneelchakraborty.com/llmshieldr/, https://github.com/ineelhere/llmshieldr, https://genai.owasp.org/llm-top-10/ BugReports: https://github.com/ineelhere/llmshieldr/issues Repository: https://ineelhere.r-universe.dev Date/Publication: 2026-05-28 18:16:03 UTC RemoteUrl: https://github.com/ineelhere/llmshieldr RemoteRef: HEAD RemoteSha: c1cf25f2bf9b0433e83e683eb4d7ec17d7d5824d NeedsCompilation: no Packaged: 2026-10-10 17:38:06 UTC; root Author: Indraneel Chakraborty [aut, cre, cph] (ORCID: ) Maintainer: Indraneel Chakraborty