docs: Add Docker usage note to README for safer execution of LLM-generated shell scripts

Author: statico

Dockerfile

@@ -0,0 +1,38 @@
+# Build stage
+FROM golang:1.24.1-alpine AS builder
+
+# Install build dependencies
+RUN apk add --no-cache git make
+
+# Set working directory
+WORKDIR /app
+
+# Copy go mod and sum files
+COPY go.mod go.sum ./
+
+# Download dependencies
+RUN go mod download
+
+# Copy source code
+COPY . .
+
+# Build the application
+RUN make build
+
+# Final stage
+FROM alpine:latest
+
+# Install runtime dependencies
+RUN apk add --no-cache ca-certificates curl bash
+
+# Set working directory
+WORKDIR /app
+
+# Copy binary from builder and install it in PATH
+COPY --from=builder /app/bin/llmscript /usr/local/bin/
+
+# Copy examples directory
+COPY --from=builder /app/examples ./examples
+
+# Set the default command
+CMD ["llmscript"]

README.md

@@ -52,6 +52,11 @@ go install github.com/statico/llmscript@latest
 
 By default, llmscript will use Ollama with the `llama3.2` model. You can configure this by creating a config file with the `llmscript --write-config` command to create a config file in `~/.config/llmscript/config.yaml` which you can edit. You can also use command-line args (see below).
 
+> [!NOTE]
+> Spooked by running LLM-generated shell scripts? Good for you! Consider running this via Docker:
+>
+> `docker run --network host -it -v "$(pwd):/data" -w /data ghcr.io/statico/llmscript examples/hello-world`
+
 ## How it works
 
 Given a script description written in natural language, llmscript works by: