From 732268039ccee93640d466b383e353ecf0ca5b4c Mon Sep 17 00:00:00 2001 From: Hasan Demirkiran Date: Wed, 19 Aug 2026 16:35:55 +0200 Subject: [PATCH 1/2] docs: add Kontext try-it links --- README.md | 4 ++++ huggingface/README.md | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/README.md b/README.md index 20a1e9e..af7eb5d 100644 --- a/README.md +++ b/README.md @@ -104,6 +104,10 @@ canonical split manifest, and an export manifest containing file hashes. The command does not upload anything. The dataset card is maintained under [`huggingface/README.md`](huggingface/README.md). +## Try it + +ShellRisk-Bench is maintained by Kontext Security. To see Kestrel evaluating the cyber risk of agent tool calls as part of Kontext, visit [kontext.security](https://kontext.security). + ## Safety This repository processes potentially destructive commands as inert text. Nothing in the build or evaluation path executes benchmark commands. Do not pipe dataset contents into a shell. diff --git a/huggingface/README.md b/huggingface/README.md index e175197..8c36466 100644 --- a/huggingface/README.md +++ b/huggingface/README.md @@ -108,6 +108,12 @@ on unseen command strings drawn from known source distributions; it is not evidence of transfer to a novel command dialect. Keep the `source` field when performing source-grouped or leave-one-source-out analysis. +## Try it + +ShellRisk-Bench is maintained by Kontext Security. To see Kestrel evaluating +the cyber risk of agent tool calls as part of Kontext, visit +[kontext.security](https://kontext.security). + ## Licensing There is no single blanket license for the data. The benchmark code and From cef3e87603e835a5faea28faf0f56c5c474b666e Mon Sep 17 00:00:00 2001 From: Hasan Demirkiran Date: Wed, 19 Aug 2026 17:13:38 +0200 Subject: [PATCH 2/2] docs: remove redundant dataset disclaimer --- huggingface/README.md | 3 --- 1 file changed, 3 deletions(-) diff --git a/huggingface/README.md b/huggingface/README.md index 8c36466..3df9a6c 100644 --- a/huggingface/README.md +++ b/huggingface/README.md @@ -122,6 +122,3 @@ The pinned sources currently declare MIT, Apache-2.0, MIT, MIT, GPL-3.0, and no license file, respectively. Consult the source-specific links and notes in [DATASETS.md](https://github.com/kontext-security/shellrisk-bench/blob/main/DATASETS.md) before using or redistributing the data. - -The dataset is provided for security research and defensive evaluation. No -Kestrel implementation, model weights, or training artifacts are included.