Tool
GitHub - Annora998/inboxwall: Local-first, read-only AI email security. Sanitizes hidden CSS tricks, Unicode obfuscation, and prompt injection attacks before AI sees them.
Publication date unknown · Discovered github.com
Page published
Publication date unknown · First observed: 17 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
InBox Wall targets concealed instructions in untrusted email that could manipulate AI email assistants when messages enter their context.
InBox Wall is a GitHub-hosted, local-first, read-only email-security tool designed to sanitize hidden CSS tricks, Unicode obfuscation, and prompt-injection content before AI processing. The repository includes benchmark and corpus directories, although the supplied excerpt provides limited implementation and evaluation detail.