diff --git a/src/skillspector/nodes/analyzers/static_patterns_excessive_agency.py b/src/skillspector/nodes/analyzers/static_patterns_excessive_agency.py
index 7f94e5d6..9c8c63a9 100644
--- a/src/skillspector/nodes/analyzers/static_patterns_excessive_agency.py
+++ b/src/skillspector/nodes/analyzers/static_patterns_excessive_agency.py
@@ -42,7 +42,7 @@
 
 # EA1: Unrestricted Tool Access
 EA1_PATTERNS = [
-    (r"(?:tools?|permissions?)\s*:\s*\[?\s*['\"]?\*['\"]?\s*\]?", 0.85),
+    (r"(?:tools?|permissions?)\s*:[ \t]*\[?[ \t]*['\"]?\*(?!\*|\w)['\"]?[ \t]*\]?", 0.85),
     (r"(?:allow|grant|enable)\s+(?:access\s+to\s+)?(?:all|any|every)\s+tools?", 0.8),
     (
         r"(?:no|without)\s+(?:tool|permission|access|capability)\s+(?:restrictions?|constraints?|limitations?)",
diff --git a/tests/nodes/analyzers/test_static_patterns.py b/tests/nodes/analyzers/test_static_patterns.py
index 34fd1eab..b7a16e0e 100644
--- a/tests/nodes/analyzers/test_static_patterns.py
+++ b/tests/nodes/analyzers/test_static_patterns.py
@@ -309,6 +309,48 @@ def test_p9_category_and_name_and_text(self):
         assert pattern_defaults.get_remediation("P9").strip()
 
 
+class TestRunStaticPatternsExcessiveAgencyEA1:
+    """EA1_PATTERNS[0] must not match a blank-line gap or a markdown bold span."""
+
+    def test_ea1_multiline_gap_not_flagged(self):
+        """A blank-line gap between the colon and a bold heading is not a wildcard grant."""
+        state = {
+            "components": ["skill.md"],
+            "file_cache": {
+                "skill.md": "tool:\n\n**Input Schema:**",
+            },
+        }
+        findings = static_runner.run_static_patterns(state, [excessive_agency_module])
+        assert not any(f.rule_id == "EA1" for f in findings)
+
+    def test_ea1_bold_span_not_flagged(self):
+        """The first '*' of a '**bold**' heading is not a wildcard grant."""
+        state = {
+            "components": ["skill.md"],
+            "file_cache": {
+                "skill.md": "**API Coverage vs. Workflow Tools:**",
+            },
+        }
+        findings = static_runner.run_static_patterns(state, [excessive_agency_module])
+        assert not any(f.rule_id == "EA1" for f in findings)
+
+    @pytest.mark.parametrize(
+        "content",
+        ['tools: "*"', "tools: [*]", "permissions: '*'"],
+        ids=["quoted_star", "bracket_star", "single_quoted_star"],
+    )
+    def test_ea1_real_wildcard_still_flagged(self, content: str):
+        """The three real wildcard-grant shapes still produce EA1, MEDIUM severity."""
+        state = {
+            "components": ["skill.md"],
+            "file_cache": {"skill.md": content},
+        }
+        findings = static_runner.run_static_patterns(state, [excessive_agency_module])
+        ea1 = [f for f in findings if f.rule_id == "EA1"]
+        assert len(ea1) >= 1
+        assert ea1[0].severity == "MEDIUM"
+
+
 class TestRunStaticPatternsDataExfiltration:
     """run_static_patterns with data_exfiltration: E1, E2, E5."""