HN Showcase
Back to browse
Prompt Armour – Real-time PII detection for AI chatbots, 100% local

Prompt Armour – Real-time PII detection for AI chatbots, 100% local

by TheAlexRider·Mar 7, 2026·13 points·2 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemShip It

Local PII redaction for ChatGPT, but dozens of prompt guardrails exist already.

Strengths
  • •Runs 100% locally in browser, zero server-side data collection or telemetry overhead
  • •Redacts before leaving device with zero friction — no popup modals or workflow interruption
  • •Real incident receipts (Samsung, Apple, Hugging Face) validate the threat model effectively
Weaknesses
  • •Market flooded with prompt guardrails (DLP platforms, Claude's built-in filtering, enterprise policy tools)
  • •No evidence of better detection than existing regex/ML-based redaction solutions available today
Category
Security
Target Audience

Developers and employees who use ChatGPT, Claude, or Gemini daily

Similar To

Lakera Guard · Prompt Armor (Lakera competing product) · OpenAI's built-in prompt filtering

Similar Projects

Security●●●Banger

OpenGuard

Drop-in LLM traffic guard with PII redaction and prompt injection detection, one command.

Solve My ProblemSlick
everlier
102mo ago
Security●●Solid

FunWithText – Free browser PII sanitizer and prompt injection scanner

Runs fully in the browser for regex-based redaction of structured PII (emails, cards, phones, API keys, IPs, SSNs) and offers an optional Claude step to catch names/addresses patterns miss. Clear placeholders like [NAME] and a privacy toggle make it practical for quick, manual workflows, and I like the Norwegian NIN/phone support. It's useful and thoughtfully privacy-first but not novel — the real win would be integrations (batch processing, editor/extension) or independent accuracy metrics for the AI step.

Solve My ProblemSlickNiche Gem
atbj
203mo ago