# qybaihe/bla

> 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 runtime behavior stays the same.

- Magnitude: 5.4 out of 10 — Early signal
- Stars: 120 total · +13 stars measured 2026-10-28, 00:02–01:27 UTC, ≈ 104 by evening
- Star trust: star growth looks organic
- Category: Security · Language: TypeScript · License: MIT · Created: 2026-10-25 · Last push: 2026-10-27
- GitHub: https://github.com/qybaihe/bla · Homepage: https://bla.tools · Page: https://gitnova.dev/en/r/qybaihe/bla

## Useful for

- Harden an Electron release build against automated reverse engineering via ASAR headers.
- Run harden on a JS bundle to exhaust a REA analyzer's resource limits.
- Check with benchmark which artifact formats are already resistant to REA.

## Why it’s here

- Star-counter measurements on 2026-10-28 (UTC), 00:02–01:27: 107 → 120 stars (+13). This is the change over that interval.
- Estimated end-of-day forecast: about +104 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 120 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #171.
- About 30 forks a day — people are taking the code.

## 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: 34
- Issues and pull requests: 22
- Watchers: 0
- Average over the last week: 56 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 12
- Latest release: bla-agents-1.4.7 (2026-10-27)

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-10-25 … 2026-10-28: 2, 27, 91, 13

## Spotted in now

- Top new repositories this week: #171

## More in this category

1. **interplains/Zero-Breach-Toolkit** — 8.1 · Early signal · Security · Python · +139 stars measured 2026-10-28, 00:02–01:26 UTC, ≈ 920 by evening
   Free offline scanner for traces of known mercenary spyware (Pegasus, Predator, Graphite, Candiru) on Windows computers, Android phones and iPhone backups. Read-only, makes no network requests, and states the limits of every check.
   Full card: https://gitnova.dev/en/r/interplains/Zero-Breach-Toolkit.md
2. **NVIDIA/SkillSpector** — 5.5 · Breakout · Security · Python · +11 stars measured 2026-10-28, 00:01–01:27 UTC, ≈ 271 by evening
   Security scanner for AI agent skills: detects vulnerabilities, malicious patterns, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before installation.
   Full card: https://gitnova.dev/en/r/NVIDIA/SkillSpector.md
3. **Cd1s/safarier** — 5.5 · Early signal · Security · Swift · Not enough measurements today
   Native macOS browser built on WebKit with isolated profiles, built-in sing-box proxy routing, and engine-level privacy protection. Lets you run dozens of independent accounts side by side while appearing as genuine Safari.
   Full card: https://gitnova.dev/en/r/Cd1s/safarier.md
4. **YuJunZhiXue/dsh-purge** — 5.1 · Steady · Security · JavaScript · +66 stars measured 2026-10-28, 00:02–01:27 UTC, ≈ 898 by evening
   A local DeepSeek Harness plugin that reversibly patches installed @deepseek-ai packages to strip built-in refusals and swap prompts per model. Intended for red-team research and robustness evaluation in an authorized local environment.
   Full card: https://gitnova.dev/en/r/YuJunZhiXue/dsh-purge.md
5. **cloudflare/security-audit-skill** — 4.9 · Steady · Security · JavaScript · +83 stars measured 2026-10-28, 00:02–01:27 UTC, ≈ 1,324 by evening
   A coding-agent skill that turns the agent into a security auditor, running a multi-phase code audit with independently verified, machine-readable findings.
   Full card: https://gitnova.dev/en/r/cloudflare/security-audit-skill.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 2026-10-28 01:38 UTC, updated every 30 minutes.