Show HN: On-device Chrome extension that blocks credential leaks to LLM chats
A new Chrome extension called Redact aims to prevent credential leaks to AI chat platforms. It intercepts pastes in real-time, scanning for sensitive information like credentials and PII before they are sent. The extension operates locally in the browser, ensuring privacy and no data is sent to external servers.
- ▪Redact catches credentials and PII before they reach AI chat platforms like ChatGPT and Claude.
- ▪The extension runs locally in the browser and does not make any network calls.
- ▪Users can choose to block or warn about sensitive data before it is pasted into chats.
Hacker News (AI / LLM) files mainly under ai. We currently carry 3,266 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Redact |
| Canonical URL | https://redact.clearformlabs.com/ |
| Publication time | Wed, 03 Jun 2026 15:08:54 +0000 |
| Retrieval time | 2026-06-03T15:22:10.213Z |
| Last seen | 2026-06-03T15:22:10.213Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | oqbk6U-IUJhX |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Stop leaking secrets to AI. Redact catches credentials and PII before they reach ChatGPT, Claude, Gemini and more. Runs in your browser. Add to Chrome Built for the chats you actually use ChatGPT Claude Copilot Perplexity Grok Mistral DeepSeek Poe ChatGPT Claude Copilot Perplexity Grok Mistral DeepSeek Poe The paste box is a credential leak waiting to happen. Chat transcripts sit on the provider's servers. You can't take it back. Three steps. Every paste. Redact intercepts pastes on supported chat sites. Detection runs in your browser. 01 Detect A local neural network scans each paste for credentials and PII. Inference runs in about 150 milliseconds. 02 Decide Set Block or Warn per data type from the popup. Defaults are tuned for engineers.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Redact.
Discussion
0 commentsMore from Redact
