Radar / AI security / Secret Guard
Secret Guard - Local LLM Gateway That Keeps Secrets Off Vendor Servers
Lightweight local LLM gateway that swaps secrets for realistic equal-length mocks in outbound requests and restores them in responses, so agents keep working while vendors never see a real key.
Why it matters
Stops coding agents like Claude Code from leaking passwords and tokens to model vendors, while agent tools keep working unchanged.
What you could build with it
A security-focused startup could integrate Secret Guard into a managed agent-runner for enterprises, offering audited, leak-proof coding agents as a compliance checkbox for banks and hospitals that ban raw secrets in prompts.
Does it hold up?
Too early to judge for real-world use: 5 stars, Show HN debut today; a full docs site with quick start exists, so a developer can try it today.
Built with Secret Guard
- Show HN: Secret Guard - a local LLM gateway; keys never leave your machinehn · Launch discussion on Hacker News (posted 2026-10-18).
- luochen1990/secret-guardgithub · 6 ★ · Local LLM gateway that redacts secrets with equal-length mocks and restores them in responses.
Learn more
First spotted on github: source.
More AI security
iFixAi: independent auditing of AI agentsIndependent AI-agent auditor: 250+ inspections across 69 misalignment categories (red teaming + operational assurance)…security · JEV 0.76Cloudflare security-audit-skill: six-phase agent-driven security audits with independently verified findingsOpen-source MIT coding-agent skill that runs a codebase through six audit phases — reconnaissance, coverage-led…security · JEV 0.74OpenAI, Anthropic and Google DeepMind jointly unveil cyber-focused safety models and safeguardsThe three rival labs disclosed weeks of behind-the-scenes coordination and jointly released a set of cyber-focused AI…security · JEV 0.73OpenAI textGrain watermarking for ChatGPT and Codex in the EUOpenAI will roll out its invisible textGrain watermarking system to ChatGPT/Codex users in the EU over the coming…security · JEV 0.65Cloudflare security-audit-skill: multi-phase security audits for coding agentsA coding-agent skill that runs multi-phase security audits with independently verified, machine-checkable findings.security · JEV 0.63LiveNerf: a pre-registered benchmark for post-release model driftOpen-source, pre-registered 30-day benchmark that detects whether Claude Opus 5.5 quietly gets worse after launch.security · JEV 0.61
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.