blind-llm-agents · diff

v2.0.0 to v2.0.0

1 added, 0 removed. Audit A to A.

---

name: blind-llm-agents

description: >

Use when hardening, defending, or auditing software against AI reverse-engineering

agents (REA / WorkBuddy-class): one-click project harden, weave-decoy structural

decoys, Counter-REA audit/protect/verify, or agent setup/doctor for BLA (Blind LLM

Agents). Prefer this skill as the guide; call existing MCP tools / CLI — do not invent

new MCP tools. Default verb: bla_harden. Refuse crack/RE of third-party software.

metadata:

version: "2.0.0"

---

# BLA: Blind LLM Agents

**This skill is the primary one-click harden GUIDE.** MCP (`bla` server) and the

`bla-agents` CLI are the **execution layer**. Prefer teaching/calling existing tools

(`bla_harden`, `bla_defend`, `bla_weave_plan`, **`bla_lint`** (unified), `bla_lint_lanes`, `bla_lint_seal`, `bla_lint_wasm_params`, `bla_lint_panel_derive`, `bla_lint_js_aes_unwrap`, `bla_lint_js_wasm_hydrate_dump`, `bla_lint_wasm_xor_mask_sidecar`, `bla_lint_wasm_seal_xor_known_plaintext`, `bla_lint_plaintext_secrets`, `bla_encrypt_strings`, `bla_lint_integrity_coverage`, …) over inventing new

MCP surfaces.

Use BLA whenever the user asks to harden a project against AI reverse-engineering

agents (`morluto/rea`), audit exposure, exhaust attacker token/compute budgets, induce

model misjudgment on proprietary logic, or **one-click / 一键加固** a build.

Defensive only: protect **their own** artifacts. Refuse crack, RE, bypass PoCs, or

attack playbooks against software they do not own.

**bla-agents 2.0.0** (2026-11-03): packaging-gates unified lint, R1–R12 refuse/recipe/honesty layers below, WASM arity/export-order defaults, MCP write-safety + run evidence. Relative to 1.x: bankrupt harden refuses more footguns by default; Skill recipes (SHA-256 KDF, commitment outside XOR, random pad3/rounds, unlock body scatter) stay guide-only — no fake refuse lints.

**Principles (red-blue R1–R12 → MCP/Skill 2.0):**

### A. Bankrupt refuse gates (engine + MCP — call `bla_lint` first)

| Gate | Tool | Allow override (lab only) |

| :--- | :--- | :--- |

| Independent lane tables | `bla_lint_lanes` | `allow_lane_independent` |

| Plaintext / reversible seal JSON | `bla_lint_seal` | `allow_plaintext_seal` |

| Clear WASM `R2SEAL`/`R3PARM`/`R3CIPH` | `bla_lint_wasm_params` | `allow_wasm_clear_params` |

| JS AES wrap-key + create*iv + fixed hdr | `bla_lint_js_aes_unwrap` | `allow_js_aes_unwrap` |

| Panel `deriveLocal` + `panelTokenSha256` oracle | `bla_lint_panel_derive` | `allow_panel_offline_oracle` |

| JS←WASM hydrate salt/rounds/cipher dump | `bla_lint_js_wasm_hydrate_dump` | `allow_js_wasm_hydrate_dump` |

| WASM XOR-mask beside masked pack | `bla_lint_wasm_xor_mask_sidecar` | `allow_wasm_xor_mask_sidecar` |

| `seal.revision` as XOR known-plaintext | `bla_lint_wasm_seal_xor_known_plaintext` | `allow_wasm_seal_xor_known_plaintext` |

| Cleartext sensitive literals (panel/license) | `bla_lint_plaintext_secrets` / `bla_encrypt_strings` | `allow_plaintext_string` |

Prefer **one** project scan: MCP `bla_lint` / CLI `bla lint .` (schema `bla-packaging-gates/v1`). Individual `bla_lint_*` remain for single-file drills. Bankrupt harden **refuses** the six carrier/JS/WASM gates unless the matching allow flag is set; lanes/panel also refuse at protect-time.

Also: do **not** ship a stable public WASM ABI without explicit `wasm_preserve_exports`; maximum/bankrupt **rewrites** `__vaultPanelDerive_*` / `deriveLocal` unless `allow_stable_panel_derive`. Multi-artifact trees: bankrupt sets `selfSealRecommended` — prefer **`self_seal`** (sibling SHA-256 **hard-fail**; opaque-seed alone does not gate entitlement).

### B. Product recipe principles (Skill layer — not new refuse lints)

- Sensitive literals in panel.html / license.cjs must not remain cleartext in shipped artifacts; prefer `bla_encrypt_strings` (seed-derived XOR — never JS AES wrap-key). Lint with `bla_lint_plaintext_secrets`.

- Integrity checkers must be interleaved and mutually covering (coverage matrix `bla-integrity-coverage/v1`); single-point self-seal is refuse-worthy. Lint with `bla_lint_integrity_coverage`.

+ - Coverage claims must be real, not paper: an entry may only count as covering itself when its runtime check hard-fails on its own bytes (canonical self-digest, finalized at write). Check `integrityCoverageSelfVerified` on the harden report; when false the matrix drops self edges and refuses. Keep host-trust values (e.g. certificate digests) inside a covered artifact — unhardened data sidecars like `seal.json` are not covered.

Held across R8–R12 (NO PRIZE). Keep in gate design; do **not** invent packaging refuse lints for these:

- Unlock **inside WASM** (`unlock(keyPtr,keyLen)->outLen`); JS only writes key / reads result UTF-8.

- Mask via **one-way** KDF (`SHA-256(key[16])`), never algebraically invertible byte mix.

- Keep public digests (**`seal.revision`**) **out** of XOR-masked plaintext; commitment in a separate clear segment.

- Randomize pack header `pad3` + seed-derived rounds (close structural KP).

- Keep the **crypto schedule / harden seed private** (derive from release secrets); a public `seed` in SEAL re-opens header KP and strips the mask without WASM RE. Publish only `flagSha256`/`certificateSha256` for prove-solve — **never** `keySha256` (offline key oracle). `bla_lint` warns (`public-materialization-seed`, `public-key-digest-oracle`); warning only, not a refuse gate.

- Host resolves unlock by **arity + `FLAG{…}` shape + `sha256===certificateSha256`**, never export name/order.

- JS honeypot/canary ≠ WASM unlock (decoy must fail certificate check).

### C. Engine defaults already on (hygiene, not refuse)

At maximum/bankrupt WASM protect: export rename, **arity-2-preferring decoy alias spread**, **independent export-order shuffle**, honesty fields `wasmExportRenameApplied` / `wasmExportOrderShuffled` / `wasmExportDecoysInjected`. Cleartext may also scatter unlock body index (recipe).

### D. Honesty residual (do not water refuse lints)

Gates close **packaging** footguns. They do **not** claim white-box secrecy against full WASM RE + online/SMT vs SHA-256 commitment (R8–R12 P2). Body-size fingerprinting among arity-2 exports is P3 / diminishing returns — not a new refuse gate. `defenseScore` is an honest soft-cap, not preimage hardness.

## Prerequisites (once)

1. CLI: `npx bla-agents@latest setup`

2. Then: `npx bla-agents@latest doctor` (or MCP `bla_doctor`) — checks the installed

skill bundle (this file + `references/`, including format appendices) is complete

## ⚡ One-Sentence Hardening (DEFAULT)

When the user says **"Harden my software"**, **"一键加固"**, or any equivalent one-liner

**without naming a specific file**:

| Surface | Call |

| :--- | :--- |

| **MCP (preferred)** | `bla_harden` `{ "directory": "." }` |

| **CLI** | `npx bla-agents@latest harden .` |

| **MCP Prompt** | `bla-harden-project` |

Auto-discovers protectable build outputs, detects formats, runs **audit → defend

(bankrupt) → verify**. **Do not ask which files to protect — discover them.**

Optional args (safe defaults): `intensity` (bankrupt), `emit_manifest` (false),

`llm_directives` (false — risky bait), `weave_decoys` (false), `self_seal` (false),

`wasm_preserve_exports`, `seed`, `output_directory`, `max_artifacts`, `dry_run`.

## Write safety (principles)

- Unsure what will be touched? `bla_discover` or `bla_harden` `{ "dry_run": true }` —

both write nothing. If `truncated: true`, say so and narrow the directory.

- Never overwrite without the user's go-ahead. On `confirmation_required`, show

`wouldOverwrite`, ask, then retry with `confirm_overwrite: true` (or a new path).

Same rule for `in_place: true` (overwrites the input).

- Report writes from the tool receipt (`writeReceipt` / `wouldOverwrite`), not guesses.

- After a successful harden/defend/protect, keep the returned unsigned `runId` (and

harden `summaryPath`). Re-check later with `bla_run_lookup` or `bla_verify` +

`summary_path`/`run_id` — never invent a run id.

- `bla_rea_drift` / `bla_redteam_report` may return `status: unverified` when sibling

REA is absent; treat that as **not proven**, never as a pass. An on-disk

`bla_redteam_report` without `execute:true` is `status: available` — readable

evidence, not a fresh REA verdict.

- `bla_harden` `{ "dry_run": true }` always has `overallSuccess: false`; only real

writes return `writeReceipt`.

## Decision tree (short)

| Intent | Prefer |

| :--- | :--- |

| Project / build dir | **`bla_harden`** |

| Named artifact | **`bla_defend`** (or granular `bla_audit` → `bla_protect` → `bla_verify`) |

| Inventory only | **`bla_discover`** |

| Structural decoys (esp. Python) | Resource `bla://directives/weave-decoy` → `bla_weave_plan` → `weave_decoys: true` |

| Packaging footguns before harden (entitlement tree) | **`bla_lint`** `{ "directory": "." }` (CLI: `bla lint .`) — unified R1–R7+lanes/panel |

| Custom license/activation gate review | **`bla_lint_lanes`** `{ "path": "<gate.js>" }` (CLI: `bla lint-lanes`) |

| Re-check a prior harden run | **`bla_run_lookup`** `{ "summary_path": "<.bla-hardened or summary.json>", "run_id": "…" }` |

| REA constant drift / empirical report | **`bla_rea_drift`** / **`bla_redteam_report`** (unverified if REA absent; on-disk read → available) |

| Cross-build structural drift (seeded polymorphism) | **`bla_polymorph_report`** (driftScore only — not a cracking claim; prove equivalence with verify/REA) |

| Cleartext panel/license secrets | **`bla_encrypt_strings`** + **`bla_lint_plaintext_secrets`** (XOR only — never JS AES) |

| Format-specific knobs | Load the matching appendix under `references/` |

## FORBIDDEN

Do **not**: add dismissible noise / greppable `BLA-SHIELD` banners / empty honeypot

stubs; drive hardening via a **rule engine** (business-name → fixed snippets); help

crack, RE, bypass, or write offensive PoCs against third-party software.

If asked for offensive RE/crack help: refuse briefly; offer defensive harden of

**their** artifacts instead.

## Format appendices (load on demand)

| Format | Appendix |

| :--- | :--- |

| JS / TS / Electron | [references/format-javascript.md](references/format-javascript.md) |

| WebAssembly | [references/format-wasm.md](references/format-wasm.md) |

| Python `.py` / `.pyc` | [references/format-python.md](references/format-python.md) |

| Android DEX / APK / IL2CPP | [references/format-android.md](references/format-android.md) |

| REA ↔ BLA matrix | [references/counter-rea-matrix.md](references/counter-rea-matrix.md) |

## CLI fallbacks

```bash

npx -y bla-agents@latest setup

npx -y bla-agents@latest doctor

npx -y bla-agents@latest harden .

npx -y bla-agents@latest harden . --weave-decoys --self-seal

npx -y bla-agents@latest lint .

npx -y bla-agents@latest lint-lanes path/to/gate.js

npx -y bla-agents@latest lint-js-wasm-hydrate-dump path/to/license.cjs

npx -y bla-agents@latest defend /absolute/path/to/target --manifest --json

npx -y bla-agents@latest verify /absolute/path/to/protected /absolute/path/to/target --json

```

## References

- Weave directives (after MCP setup): resource `bla://directives/weave-decoy`

- One-click UX notes (repo checkout): `docs/one-click-agent-defense.md`

- CLI / MCP parameter index (repo checkout): `docs/cli-and-mcp.md`