Radar / AI security / BLA

BLA: adversarial defense shield that poisons, exhausts and hallucinates AI reverse-engineering agents

TypeScript shield protecting binaries, Electron apps, JS bundles, Python and WebAssembly against AI reverse-engineering agents such as REA, via Poison, Exhaust and Hallucinate stages.

new launchsecurity · complianceJEV traction 0.47qybaihe/bla · 1,537 ★added 2026-10-31
Open BLA →View on the radar

Why it matters

A defense built specifically for the new threat of AI agents that decompile and analyze shipped code, gaining about 650 stars a day within a week of release.

What you could build with it

An indie developer shipping a desktop app could wrap a release build with BLA before distribution, then test whether a reverse-engineering agent still recovers API keys or proprietary logic from the shipped binary.

Does it hold up?

Too early to judge: released 25 Oct with fast growth, but no independent red-team evaluation of the shield against current reverse-engineering agents has been published yet.

Built with BLA

Learn more

official docs →

First spotted on github: source.

More AI security

NVIDIA SkillSpector: security scanner for AI agent skills, trending againNVIDIA's open-source SkillSpector scanner is trending on GitHub today: it audits AI agent skills before installation…security · JEV 0.75Shannon: open-source AI pentester that reports only vulnerabilities it can actually exploitCLI agent that combines source-code analysis with live exploitation against web apps and APIs under a 'no exploit, no…security · JEV 0.71Anthropic sandbox-runtime: OS-level sandboxing for AI agents, no containers requiredAnthropic's sandbox-runtime (srt) is trending with developers this week: an open-source tool that wraps any process in…security · JEV 0.45VoidAccess: open-source, self-hosted dark web OSINT platformSelf-hosted dark-web OSINT platform (892 stars) that takes automated threat intelligence from query to a graph…security · JEV 0.42Cisco Project Quarry: open-source behavior detection engine for AI agentsCisco open-sourced Project Quarry on 28 Oct 2026: a behavior detection engine that watches AI agents at the session…security · JEV 0.42PlugVetAn independent public directory that grades AI agent skills, plugins, and MCP servers with evidence-backed hygiene…security · JEV 0.42

Get the week's best AI launches, plus 3 ideas worth building

One email every Saturday. Ranked by traction, not hype. Free.