[FEATURE] Claude should proactively suggest input sanitization when building data pipelines

Preflight Checklist

• [x] I have searched existing requests and this feature hasn't been requested yet
• [x] This is a single feature request (not multiple features)

Problem Statement

When working with Claude Code to build a data processing pipeline (in my case, processing meeting transcripts from Google Drive), we went through several iterations of debugging production failures before Claude suggested adding input sanitization.

The issues we encountered:

• Control characters (null bytes, form feeds) breaking JSON parsing
• Zero-width Unicode characters (BOM, ZWJ, ZWNJ) causing invisible issues
• Numeric HTML entities not being decoded
• Inconsistent line endings (CRLF vs LF)

These are well-known, common issues when processing external data. Sanitization should have been part of the initial pipeline design, not added after debugging failures in production.

Would save significant debugging time and prevent production issues that are easily avoidable with upfront sanitization. This is also a clear security item.

Proposed Solution

When Claude helps build any pipeline that ingests external data (files, APIs, user input, etc.), it should proactively suggest input sanitization as a foundational step, including:

• Control character removal
• Unicode normalization
• Encoding handling
• Line ending normalization

This is table stakes for robust software. Claude should treat it as a default consideration, similar to how it considers error handling or input validation.

Alternative Solutions

_No response_

Priority

Critical - Blocking my work

Feature Category

File operations

Use Case Example

_No response_

Additional Context

_No response_