feat(okf): resource-URL https allowlist reject-gate (T3, TDD, +10)

tests/test_okf.py

@@ -21,8 +21,10 @@ from llm_ingestion_guard.okf import (
     parse_frontmatter,
     scan_concept,
     validate_concept_path,
+    validate_resource_url,
     OKFFrontmatterError,
     OKFPathError,
+    OKFResourceError,
 )
 from llm_ingestion_guard.report import Report
 
@@ -200,3 +202,57 @@ def test_validate_concept_path_rejects_backslash():
 def test_validate_concept_path_rejects_non_md():
     with pytest.raises(OKFPathError):
         validate_concept_path("tables/users.txt")
+
+
+# --- T3: resource-URL https allowlist reject-gate ----------------------------
+# OKF imposes NO scheme constraint on `resource` (verified against SPEC.md), so
+# this default-deny allowlist is the only gate: accept https, reject all else
+# BEFORE commit — reject, not defang (that is neutralize's job, for human audit).
+
+def test_validate_resource_url_accepts_https():
+    assert validate_resource_url("https://example.com/asset") == "https://example.com/asset"
+
+
+def test_validate_resource_url_accepts_https_case_insensitive_scheme():
+    assert validate_resource_url("HTTPS://example.com") == "HTTPS://example.com"
+
+
+def test_validate_resource_url_rejects_http():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("http://example.com/asset")
+
+
+def test_validate_resource_url_rejects_data():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("data:text/html,<script>alert(1)</script>")
+
+
+def test_validate_resource_url_rejects_javascript():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("javascript:alert(1)")
+
+
+def test_validate_resource_url_rejects_file():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("file:///etc/passwd")
+
+
+def test_validate_resource_url_rejects_ftp():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("ftp://host/x")
+
+
+def test_validate_resource_url_rejects_schemeless():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("example.com/asset")
+
+
+def test_validate_resource_url_rejects_empty():
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("")
+
+
+def test_validate_resource_url_rejects_embedded_whitespace():
+    # a space-split URL can smuggle a second target past a naive consumer parser
+    with pytest.raises(OKFResourceError):
+        validate_resource_url("https://good.example/x javascript:alert(1)")