bla
BLA is an adversarial defense tool that protects software from AI reverse engineering agents.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 1.4k
- Source
- mcp-github
- Repository
- github.com/qybaihe/bla
Overview
BLA (Blind LLM Agents) is an adversarial defense tool designed to protect binary files, Electron applications, JS bundles, Python, and WebAssembly from attacks by AI reverse engineering agents (such as REA). It confuses analyzers by embedding syntactically valid decoys, exhausting resource budgets, and generating hallucinations, all while maintaining unchanged runtime behavior. Developers can integrate it into their projects with a simple command or via MCP/Agent skills to enhance software security.
Capabilities
- ▪Embed syntactically valid decoys
- ▪Exhaust resource budgets
- ▪Generate hallucinations to mislead analyzers
- ▪Maintain unchanged runtime behavior
Use cases
Setup
npx bla-agents setup
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
What types of files does BLA support?
Supports binary files, Electron apps, JS bundles, Python, and WebAssembly.
How do I use BLA to protect my software?
Run the command `npx bla-agents harden .`.
Related skills
valaxy
A static blog framework based on Vue 3 and Vite with AI capabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.