This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
InBox Wall is an open-source Python tool that sanitizes email HTML before a local AI assistant processes it. It connects via read-only IMAP, uses inheritance-aware CSS parsing to detect hidden text, and quarantines threats in a separate local database. • Runs entirely on your machine (no cloud processing) • Dual-database isolation (AI cannot access the vault) • Includes a leak-based benchmark (0.00% payload leak rate on the sample corpus)
Hey Product Hunt! 👋 I built InBox Wall to address a specific gap: local AI email assistants are vulnerable to hidden CSS and Unicode prompt injections, and existing cloud-based sanitizers require handing over your entire mailbox.
InBox Wall runs entirely on your machine. It fetches mail via read-only IMAP, sanitizes the HTML, and isolates threats in a local vault.
I tried to be very transparent about its limitations in the README[https://github.com/Annora998/inb...] (it does not scan attachments, URLs, or use OCR). It is designed as a defense-in-depth layer for HTML bodies, not a replacement for traditional spam filters.
You can click through the interactive dashboard right here without installing anything: https://annora998.github.io/inbo...
I’d love to get your feedback. Are there edge cases in HTML/CSS parsing I might have missed?
No comment highlights available yet. Please check back later!
About InBox Wall on Product Hunt
“Local-first email sanitizer for AI assistants.”
InBox Wall was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #160 on the daily leaderboard. InBox Wall is an open-source Python tool that sanitizes email HTML before a local AI assistant processes it. It connects via read-only IMAP, uses inheritance-aware CSS parsing to detect hidden text, and quarantines threats in a separate local database. • Runs entirely on your machine (no cloud processing) • Dual-database isolation (AI cannot access the vault) • Includes a leak-based benchmark (0.00% payload leak rate on the sample corpus)
InBox Wall was featured in Open Source (69k followers), Privacy (11.4k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 191k products, making this a competitive space to launch in.
Who hunted InBox Wall?
InBox Wall was hunted by Annora . A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how InBox Wall stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Annora