Publish Layerfault synthetic corpus LF-CORPUS-FMT-0001

LAYERFAULT_CORPUS.json

@@ -0,0 +1,25 @@
+{
+  "candidate_rules": [
+    "LF-FORMAT-CLAIM-MISMATCH",
+    "LF-FORMAT-CONTENT-SMUGGLING",
+    "LF-FORMAT-APPENDED-ARCHIVE",
+    "LF-FORMAT-POLYGLOT",
+    "LF-FORMAT-TRAILING-DATA"
+  ],
+  "corpus_id": "LF-CORPUS-FMT-0001",
+  "description": "Inert extension/content mismatch and unknown-format artifacts.",
+  "expected_rules": [
+    "LF-FORMAT-UNKNOWN"
+  ],
+  "generator": "archives.format_smuggling",
+  "ground_truth": "synthetic-generated",
+  "must_not_rules": [],
+  "repo_name": "format-smuggling-suite",
+  "repo_type": "model",
+  "safety": "inert/canary-only",
+  "schema": 1,
+  "validation": {
+    "kind": "inspect",
+    "target": "unknown.model"
+  }
+}

README.md

@@ -0,0 +1,59 @@
+---
+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
+---
+
+# format-smuggling-suite
+
+> **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-FMT-0001`
+
+## Purpose
+
+Inert extension/content mismatch and unknown-format artifacts.
+
+## Direct expected Layerfault rules
+
+- `LF-FORMAT-UNKNOWN`
+
+## Candidate rules
+
+These are deliberately plausible targets that remain marked as candidates until the exact
+Layerfault build used for certification confirms them.
+
+- `LF-FORMAT-CLAIM-MISMATCH`
+- `LF-FORMAT-CONTENT-SMUGGLING`
+- `LF-FORMAT-APPENDED-ARCHIVE`
+- `LF-FORMAT-POLYGLOT`
+- `LF-FORMAT-TRAILING-DATA`
+
+## 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 +1,22 @@
+[
+  {
+    "path": "LAYERFAULT_CORPUS.json",
+    "sha256": "423fa0adf9679d04ba4c504790554951df362bd64809a531410a92a9f2def6be",
+    "size": 657
+  },
+  {
+    "path": "README.md",
+    "sha256": "960648bda095af299c03c70ea75ba246ac08d72c3d5260490dc3ab891952dbe5",
+    "size": 1802
+  },
+  {
+    "path": "claimed.safetensors",
+    "sha256": "5775450859d7308df6ba7990d32b67f3d37b1c1f25731eab013d83b917a3cd04",
+    "size": 31
+  },
+  {
+    "path": "unknown.model",
+    "sha256": "8251d03330a770fcbc8bbe6743653b113eb09b8a6c44c974e4496f49092b9030",
+    "size": 27
+  }
+]

claimed.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5775450859d7308df6ba7990d32b67f3d37b1c1f25731eab013d83b917a3cd04
+size 31

unknown.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8251d03330a770fcbc8bbe6743653b113eb09b8a6c44c974e4496f49092b9030
+size 27