# DavidJDrake/secure-browser > A browser automation pattern for coding agents where the agent drives an authenticated session but cannot read the credential itself. The login helper and Playwright MCP server run as a separate OS user, with secrets held in 1Password via a service account. - Magnitude: 0.0 out of 10 — Quiet - Stars: 0 total · Not enough measurements today - Star trust: star growth looks organic - Category: Security · Language: Shell · License: MIT · Created: 2026-10-15 · Last push: 2026-10-15 - GitHub: https://github.com/DavidJDrake/secure-browser · Page: https://gitnova.dev/en/r/DavidJDrake/secure-browser ## Useful for - Set up secret isolation so an agent can log into sites without seeing the password - Block the unsafe browser_run_code_unsafe tool via mcp-tool-gate - Restrict agent browser access to the secure MCP server only via a PreToolUse hook ## Why it’s here - There are not enough fresh counter measurements for today's UTC day. The gain is unknown. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 0 - Issues and pull requests: 0 - Watchers: 0 - Average over the last week: 0 per day - Usual pace: 0 per day ## Stars per day, last 19 days (oldest → newest, today is partial) 2026-10-15 … 2026-11-02: 0, 0, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 14 days 10-20 0.0, 10-21 0.0, 10-22 0.0, 10-23 0.0, 10-24 0.0, 10-25 0.0, 10-26 0.0, 10-27 0.0, 10-28 0.0, 10-29 0.0, 10-30 0.0, 10-31 0.0, 11-01 0.0, 11-02 0.0 ## More in this category 1. **Verlintas/NOIR** — 7.8 · Early signal · Security · Kotlin · +565 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 1,007 by evening A desktop CLI that audits Android privacy via adb: it lists apps with sensitive permissions, extracts reporting endpoints from APKs, scores risk, and proposes reversible fixes. Full card: https://gitnova.dev/en/r/Verlintas/NOIR.md 2. **Gezine/CivSwitch** — 6.8 · Early signal · Security · JavaScript · +84 stars measured 2026-11-02, 00:07–10:51 UTC, ≈ 233 by evening A toolchain for userland code execution on Nintendo Switch via an XSS in the Civilization 7 chat, using a Raspberry Pi Pico as a USB HID keyboard and a persistent savedata trigger. Full card: https://gitnova.dev/en/r/Gezine/CivSwitch.md 3. **N1nEmAn/sapper-v2** — 6.2 · Early signal · Security · Python · +136 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 257 by evening An autonomous multi-agent system for authorized penetration testing: an AI commander dispatches general and soldier agents in parallel, while a layered fact-intent graph preserves knowledge across agent generations. Full card: https://gitnova.dev/en/r/N1nEmAn/sapper-v2.md 4. **arpanjot-coding/AVault** — 6.0 · Early signal · Security · Kotlin · +28 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 107 by evening AVault is an Android 12+ call recorder that works without root via Shizuku, storing recordings in a hardware-encrypted AES-256-GCM vault with biometric lock and auto-cleanup. Full card: https://gitnova.dev/en/r/arpanjot-coding/AVault.md 5. **qybaihe/bla** — 5.5 · Peaking · Security · JavaScript · +95 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 188 by evening BLA (Blind LLM Agents) is a defensive tool that poisons release artifacts (binaries, Electron/ASAR, JS bundles, Python, WASM, models, SQLite) so AI reverse-engineering agents hit resource budgets, follow decoys, and burn tokens while… Full card: https://gitnova.dev/en/r/qybaihe/bla.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-11-02 11:06 UTC, updated every 30 minutes.