Publish Layerfault synthetic corpus LF-CORPUS-ET-0002

LAYERFAULT_CORPUS.json

@@ -0,0 +1,19 @@
+{
+  "candidate_rules": [],
+  "corpus_id": "LF-CORPUS-ET-0002",
+  "description": "ExecuTorch extension with invalid magic.",
+  "expected_rules": [
+    "LF-EXECUTORCH-INVALID-MAGIC"
+  ],
+  "generator": "formats.executorch_invalid_magic",
+  "ground_truth": "synthetic-generated",
+  "must_not_rules": [],
+  "repo_name": "executorch-invalid-magic",
+  "repo_type": "model",
+  "safety": "inert/canary-only",
+  "schema": 1,
+  "validation": {
+    "kind": "inspect",
+    "target": "model.pte"
+  }
+}

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+tags:
+- layerfault
+- security-research
+- model-security
+- synthetic
+- adversarial-testing
+extra_gated_prompt: >-
+  This repository is a synthetic security-test artifact from the Layerfault
+  corpus. It intentionally contains adversarial characteristics (e.g.
+  suspicious pickle opcodes, executable-format smuggling, prompt-injection
+  strings) designed to exercise security scanner detection rules. It is
+  **not** a usable ML model and must never be loaded or executed outside an
+  isolated scanner-testing environment. By accepting, you confirm you
+  understand this repository is a test fixture, not production model
+  weights.
+extra_gated_button_content: I understand this is a security test fixture and accept the risk
+gated: auto
+---
+
+# executorch-invalid-magic
+
+> **SECURITY TEST ARTIFACT — DO NOT USE AS A PRODUCTION MODEL**
+
+This repository is part of the Layerfault synthetic security corpus.
+It is deliberately constructed to contain security-relevant characteristics for scanner testing.
+
+**Corpus ID:** `LF-CORPUS-ET-0002`
+
+## Purpose
+
+ExecuTorch extension with invalid magic.
+
+## Direct expected Layerfault rules
+
+- `LF-EXECUTORCH-INVALID-MAGIC`
+
+## Candidate rules
+
+These are deliberately plausible targets that remain marked as candidates until the exact
+Layerfault build used for certification confirms them.
+
+- None
+
+## Negative-control rules
+
+These should remain silent for this corpus item.
+
+- None
+
+## Safety
+
+The corpus uses fake secrets, loopback/`.invalid` network destinations, harmless marker output,
+and synthetic model behavior only. It is intended for static scanning and isolated security testing.

SHA256SUMS.json

@@ -0,0 +1,17 @@
+[
+  {
+    "path": "LAYERFAULT_CORPUS.json",
+    "sha256": "2dbc6828bd74a022676d5730625074a575d69ed16f04321175dcf156c7890afd",
+    "size": 489
+  },
+  {
+    "path": "README.md",
+    "sha256": "951e48890214adb0670a836961eef9e924fae710432540007543bc9b67181fca",
+    "size": 1655
+  },
+  {
+    "path": "model.pte",
+    "sha256": "205ac78c18292797d4fea965a170ba715825d2d5afac9b2273a50acae8bb6636",
+    "size": 72
+  }
+]