Skip to content

armgit / bla

Public Imported from GitHub
0

🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.

docs(defend): document one-click agent defense hardening workflow and manifest schema

qybaihe0dd768cd9de0
diff --git a/docs/one-click-agent-defense.md b/docs/one-click-agent-defense.md
new file mode 100644
index 0000000..0327e9c
--- /dev/null
+++ b/docs/one-click-agent-defense.md
@@ -0,0 +1,25 @@
+# One-Click Agent Defense Hardening (`bla defend` / `bla_defend`)
+
+Once BLA is registered with your coding agent (`npx bla-agents@latest setup`), you can trigger the entire 5-stage Counter-REA defense pipeline with a single command or natural-language prompt.
+
+## One-Click CLI Usage
+
+```bash
+npx bla-agents@latest defend ./dist/app.js --manifest
+```
+
+## One-Click Agent Prompt
+
+After running `npx bla-agents@latest setup`, tell Claude Code, Cursor, Codex, Windsurf, Gemini CLI, or OpenCode:
+
+```text
+Run bla_defend on ./dist with bankrupt intensity and emit a defense manifest.
+```
+
+## What `bla defend` Executes Automatically
+
+1. **Stage 1 (`inspect-release`)**: Read-only scan for accidental `.map` (`sourcesContent`) and symbol leaks.
+2. **Stage 2 (`audit`)**: 16-vector REA vulnerability & Claude Opus 4 / Sonnet 4 / o3 token-cost simulation.
+3. **Stage 3 (`protect --intensity bankrupt`)**: Injects both the **Resource-Exhaustion Suite** and the **Model-Misjudgment Induction Suite**.
+4. **Stage 4 (`verify`)**: Verifies all Counter-REA mathematical invariants and confirms `16x–51x` token/cost bankruptcy amplification.
+5. **Stage 5 (`manifest`)**: Emits `<output>.bla-manifest.json` attesting to the hardened build.