Skip to content

armgit / bla

Public Imported from GitHub
0

πŸ›‘οΈ BLA (Blind LLM Agents) β€” Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust -> Hallucinate.

docs: sync skill/CLI/one-click for self-seal, lint-lanes, WASM rename

qybaihe97c1fb2734d7
diff --git a/.agents/skills/blind-llm-agents/SKILL.md b/.agents/skills/blind-llm-agents/SKILL.md
index 34a3a50..c1aca30 100644
--- a/.agents/skills/blind-llm-agents/SKILL.md
+++ b/.agents/skills/blind-llm-agents/SKILL.md
@@ -7,7 +7,7 @@ description: >
Agents). Prefer this skill as the guide; call existing MCP tools / CLI β€” do not invent
new MCP tools. Default verb: bla_harden. Refuse crack/RE of third-party software.
metadata:
- version: "1.3.0"
+ version: "1.3.1"
---
# BLA: Blind LLM Agents
@@ -79,6 +79,29 @@ happy paths, call-graph entanglement). JS AST weave is already on; Python `.py`/
customer-def structural weave activates when `weave_decoys: true`. See
[docs/weave-decoy-mcp.md](../../../docs/weave-decoy-mcp.md).
+
+## Optional stronger path: self-seal (#40.5)
+
+When the user wants sibling-module integrity / anti-tamper binding on **JS/Node**
+targets (or says self-seal / θ‡ͺ密封):
+
+1. CLI: add `--self-seal` to `harden` / `defend` / `protect`
+2. MCP: `self_seal: true` on `bla_harden` / `bla_defend` / `bla_protect`
+3. Config: `"selfSeal": true` in `.blarc` (ORs with the flag)
+
+Off by default. Browser builds soft-skip (digest=0). Pair with weave decoys when
+Python structural weave is also desired.
+
+## Lane-independence footgun lint (#40.1)
+
+Before shipping a custom license/activation gate, run:
+
+`npx bla-agents lint-lanes path/to/gate.js`
+
+Heuristic warn only (exit 2 when findings). Prefer whole-key chained mixing
+(no per-lane oracle) β€” see Meridian DESIGN / issue #40. Not RE advice.
+
+
## FORBIDDEN for executing agents
Do **not**:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index a7c7dcc..8de6b0d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
+### Added
+- **Self-seal (#40.5):** opt-in CLI `--self-seal` / MCP `self_seal` / `.blarc selfSeal` injects Node sibling-module + env-fingerprint integrity binding into JS AST shield and entangles the opaque-predicate seed.
+- **WASM export rename (#40.3):** `protectWasmBinary` renames internal-looking exports at maximum/bankrupt (preserve public ABI via `preserveExports`); returns `exportsRenamed`.
+- **Lane-independence lint (#40.1):** `bla lint-lanes <file>` heuristic warn for per-lane oracle footguns; `lintLaneIndependence()` API.
+- **Sidecar entanglement DESIGN + planner stub:** `docs/design/sidecar-entry-entanglement.md` + `planSidecarEntanglement()`.
+- **`.blarc weaveDecoys` / `selfSeal` schema parity** with CLI/MCP flags.
+
+### Changed
+- **defenseScore honesty (#40.6):** soft-caps + gap annotations when WASM rename / self-seal / numeric template gaps still apply; SEAL/verify text clarifies score β‰  preimage hardness.
+- **Opaque-predicate seed (#40.4):** ~28-bit PRNG material (no hrtime/Date.now); `recommendOpaqueSeedBinding()` helper.
+- **Native header templates:** scrub classic `0x9e3779b9` probe from emit-headers output.
+
+
### Changed
- **`blind-llm-agents` skill β†’ v1.3.0**: skill is the primary one-click harden GUIDE
diff --git a/docs/cli-and-mcp.md b/docs/cli-and-mcp.md
index d27d425..fc08de8 100644
--- a/docs/cli-and-mcp.md
+++ b/docs/cli-and-mcp.md
@@ -34,6 +34,10 @@ For coding agents, the **[`blind-llm-agents` skill](../.agents/skills/blind-llm-
Project config parity: set `"weaveDecoys": true` in `.blarc` / `bla.config.json` (schema `bla.config.v1.json`) to enable the same flag without repeating `--weave-decoys` / MCP `weave_decoys` on every invoke. CLI/MCP flags still OR with the config value.
+Opt-in **self-seal** (issue #40.5): CLI `--self-seal`, MCP `self_seal`, `.blarc` `"selfSeal": true`. Injects a Node self-integrity preamble (module + optional sibling paths + env fingerprint) and folds the digest into the opaque-predicate seed for JS/Node targets.
+
+Heuristic **lane-independence lint** (issue #40.1): `bla lint-lanes <file>` warns when gate code looks like independent per-lane checks. Defensive guidance only β€” prefer whole-key chained mixing.
+
### MCP Resources
- `bla://directives/weave-decoy` β€” weave-decoy theory + executor checklist (Markdown).
diff --git a/docs/counter-rea-deception.md b/docs/counter-rea-deception.md
index 388929f..281df2b 100644
--- a/docs/counter-rea-deception.md
+++ b/docs/counter-rea-deception.md
@@ -37,3 +37,8 @@ JS AST already weaves; Python `.py` with `weave_decoys:true` structurally weaves
Executable theory + MCP: [`weave-decoy-mcp.md`](./weave-decoy-mcp.md),
resource `bla://directives/weave-decoy`, tool `bla_weave_plan`, flag
`weave_decoys`.
+
+
+## WASM export rename (#40.3)
+
+`protectWasmBinary` can rename non-public / internal-looking exports while preserving names listed in `preserveExports`. At `maximum`/`bankrupt`, internal-looking names (`__*`, `debug_*`, …) are renamed by default. Forced full rename: `renameNonPublicExports: true` with an explicit preserve list for the public ABI. Returns `exportsRenamed` for glue updates.
diff --git a/docs/one-click-agent-defense.md b/docs/one-click-agent-defense.md
index 6dabb56..6de9575 100644
--- a/docs/one-click-agent-defense.md
+++ b/docs/one-click-agent-defense.md
@@ -68,3 +68,8 @@ See [`weave-decoy-mcp.md`](./weave-decoy-mcp.md). Do **not** add dismissible
- [CLI and MCP](./cli-and-mcp.md)
- [Counter-REA matrix](../.agents/skills/blind-llm-agents/references/counter-rea-matrix.md)
+
+
+## Opt-in self-seal (#40.5)
+
+Pass `--self-seal` / MCP `self_seal: true` / `.blarc` `"selfSeal": true` so JS/Node harden paths inject sibling-module integrity binding and entangle the opaque seed. Off by default.