Security●●●Banger
Kasbah Guard – Free browser extension that catches secrets on GenAI
ML-based secret detection stops real leaks before ChatGPT sees them; better accuracy than regex tools.
Solve My ProblemWizardry
AdnaneA
103mo ago
Back to browse
GitHub Repository
HTTPS proxy that intercepts AI prompts and blocks sensitive data before it reaches Copilot, OpenAI, or Anthropic
6 starsGo
Prompt Guard–MitM proxy that blocks secrets before they reach AI APIs
by chaudharydeepak·Mar 26, 2026·3 points·5 comments
AI Analysis
●●SolidSolve My ProblemNiche Gem
MITM proxy catches leaked secrets before they hit AI APIs — better than post-hoc scanning.
Strengths
- •Wire-level interception means zero code changes to existing AI tooling.
- •12 built-in rules for AWS keys, SSNs, private keys catch common leaks.
- •SQLite audit log persists flagged prompts across restarts for compliance.
Weaknesses
- •Requires CA cert installation — friction for teams without MDM.
- •Only targets three AI services; misses local LLMs and other providers.
Category
Target Audience
Developers using AI coding assistants
Similar To
GitGuardian · Gitleaks · Detectify
Similar Projects
Developer Tools●●Solid
Built an open-source local firewall for AI coding agents
Hard budget kill-switch stops runaway agent costs before the bill hits.
Solve My ProblemDark Horse
ashishp15
226d ago
Security●●●Banger
ClawShield – Open-source security proxy for AI agents (Go, eBPF)
Defense-in-depth AI agent firewall: proxy + eBPF kernel + three-tier injection detection.
WizardrySolve My Problem
sleuthco
223mo ago
Security●●Solid
Agent Memory Guard – OWASP defense for AI agent memory poisoning
OWASP reference implementation for ASI06 memory poisoning with LangChain and AutoGen integrations.
Solve My ProblemBig Brain
vgudur297
3016d ago
Developer Tools●●●Banger
TokenShield – cut your Claude Code bill 40-70%
Diff-based file reads and conversation deduplication slash token bills by 40%.
Big BrainSolve My ProblemShip It
curatedmcp
3327d ago
Security●●Solid
Senthex AI firewall for LLM API calls (one line of code, 16ms overhead)
Heuristic-based shields beat LLM-in-the-loop detectors on speed, but Lakera Guard already owns this space.
Solve My ProblemSlick
yohann_senthex
202mo ago