feat(active-content,okf): bound the last two detection surfaces

`scan_active_content` called directly and `okf.link_graph` were the two surfaces
still reading attacker-supplied text with no cap — the first reached by an
adapter that wants the active-content classes alone, the second running a
`findall` over every body in a bundle. Both are detection-shaped, so they
truncate and flag rather than raise the way the transform surfaces do: what a
detector shortens is its own coverage, not the caller's content.

Truncation is only honest if it is visible, so neither goes quiet: the scanner
emits `active:oversize-input` (LLM10), and `link_graph` records
`(from_id, body_length)` in `LinkGraphResult.truncated` — the field that lets a
caller tell "no links past here" from "no links read past here".

Reached through `scan_output`, the text is already under that surface's cap and
`max_scan_chars` is now passed down, so the flag is raised once, there.

docs/LIMITATIONS.md

@@ -302,21 +302,25 @@ items; this is the full list, each with the mechanism.
   *closes* around a long body, and a run of plain characters carrying no anchor
   at all.
 
-- **Two detection surfaces still accept unbounded input; the transform surfaces
+- **Every surface now bounds its input, but not all of them the same way.**
-  no longer do.** Unreleased, on `main` at `2d98d68`: `sanitize`, `fence` and
+  `sanitize`, `fence` and `neutralize` raise `OversizeInputError` above
-  `neutralize` raise
+  `MAX_INPUT_CHARS` (1 000 000) rather than returning a partially transformed
-  `OversizeInputError` above `MAX_INPUT_CHARS` (1 000 000) rather than returning
+  document, which bounds the whole input path — `sanitize` is step 1 of
-  a partially transformed document, which bounds the whole input path — `sanitize`
+  `prepare_input`, and it only ever removes, so everything after it is already
-  is step 1 of `prepare_input`, and it only ever removes, so everything after it
+  under the cap. They reject rather than truncate because they return *content*:
-  is already under the cap. They reject rather than truncate because they return
+  a shortened document is silent data loss, and a transformed prefix followed by
-  *content*: a shortened document is silent data loss, and a transformed prefix
+  an untransformed tail is a bypass an attacker positions the payload into. The
-  followed by an untransformed tail is a bypass an attacker positions the payload
+  detection surfaces truncate instead, which costs only detection in the tail —
-  into. The scanners keep truncating, which costs only detection in the tail.
+  `scan_lexicon` / `scan_output` always have, and as of 0.4.0
-  What remains uncapped is `scan_active_content` **called directly** (reached
+  `scan_active_content` **called directly** does too (reached through
-  through `scan_output` it inherits that cap) and the okf link graph, whose cost
+  `scan_output` it inherits that surface's cap and is not flagged twice), as does
-  is a bundle-wide `findall` over every document body. Both are detection-shaped,
+  `okf.link_graph`, whose cost was a bundle-wide `findall` over every document
-  so the scanners' truncate-and-flag mechanism transfers to them unchanged — that
+  body. **What truncation costs is worth naming: past the cap, "no finding" means
-  is a mechanical follow-up, not a policy question, and it is not yet done.
+  "not looked at".** Each says so rather than staying silent — the scanners emit
+  an `oversize-input` finding (`active:oversize-input`, OWASP LLM10), and
+  `link_graph` records `(from_id, body_length)` in `LinkGraphResult.truncated`,
+  which is what lets a caller tell "no links past here" apart from "no links
+  *read* past here".
 
 ## The six documented gaps (tracked by the coverage matrix)
 

src/llm_ingestion_guard/active_content.py

@@ -60,12 +60,13 @@ from urllib.parse import urlsplit
 from .calibration import (
     ACTIVE_CONTENT_ORDINARY_SEVERITY as _ORDINARY_SEVERITY,
     ACTIVE_CONTENT_SEVERITY as _SEVERITY,
+    MAX_SCAN_CHARS,
     URL_OPAQUE_ENTROPY_H as _OPAQUE_H,
     URL_OPAQUE_HEX_MIN_LEN as _OPAQUE_HEX_LEN,
     URL_OPAQUE_MIN_LEN as _OPAQUE_MIN_LEN,
 )
 from .entropy import is_hex_blob, shannon_entropy, try_decode_base64
-from .report import Finding, Report, Source
+from .report import Finding, Report, Severity, Source
 
 # --- URL defang (shared primitive) -------------------------------------------
 # Rewrite a URL to a form no renderer will resolve, while keeping it readable.
@@ -267,15 +268,35 @@ def is_ordinary_url(url: str) -> bool:
 # shares them.
 
 
-def scan_active_content(text: str, source: Source = Source.OUTPUT) -> Report:
+def scan_active_content(
+    text: str,
+    source: Source = Source.OUTPUT,
+    max_scan_chars: int = MAX_SCAN_CHARS,
+) -> Report:
     """Report active-content constructs with an external target in ``text``.
 
     Report-only (design principles 3 & 4): the input is never mutated and no
     disposition is rendered here. Labels are ``active:<class>``; severities
     mirror ``neutralize``'s (image / raw-html / data-uri HIGH, links MEDIUM).
+
+    Self-safety (OWASP LLM10): the scanned length is capped once, and an
+    ``active:oversize-input`` finding announces that the tail went unread. It
+    truncates rather than raising the way the transform surfaces do — what a
+    detector shortens is its own coverage, not the caller's content. Reached
+    through :func:`~llm_ingestion_guard.output.scan_output` the text is already
+    under that surface's cap, so the flag is raised once, there.
     """
     report = Report()
 
+    if len(text) > max_scan_chars:
+        report.add(Finding(
+            label="active:oversize-input", severity=Severity.MEDIUM,
+            source=source, detector="active_content", count=len(text),
+            owasp="LLM10",
+            evidence=f"input {len(text)} chars exceeds cap {max_scan_chars}; scanned prefix only",
+        ))
+        text = text[:max_scan_chars]
+
     def _flag(cls: str, hits: list[tuple[str, bool]]) -> None:
         """Report one finding for ``cls``, graded by its *worst* member.
 

src/llm_ingestion_guard/okf.py

@@ -26,6 +26,7 @@ import re
 from dataclasses import dataclass
 from enum import Enum
 
+from .calibration import MAX_SCAN_CHARS
 from .output import scan_output
 from .report import Report, Source
 from .disposition import Trust, Disposition, Policy, decide
@@ -428,12 +429,15 @@ class LinkGraphResult:
     signal of §7.2 (a link planted to a not-yet-written concept). ``rejected`` —
     ``(from_id, target, reason)`` for links refused outright (dangerous scheme or
     bundle escape). ``resolved`` — ``(from_id, target_concept_id)`` for links to
-    concepts present in the bundle.
+    concepts present in the bundle. ``truncated`` — ``(from_id, body_length)`` for
+    bodies read only as far as the scan cap, so a caller can tell "no links past
+    here" apart from "no links *read* past here" (OWASP LLM10).
     """
 
     dangling: tuple
     rejected: tuple
     resolved: tuple
+    truncated: tuple = ()
 
 
 def extract_link_targets(body):
@@ -475,14 +479,20 @@ def resolve_link(target, from_concept_id):
     return normalized[: -len(".md")]
 
 
-def link_graph(bundle):
+def link_graph(bundle, max_scan_chars=MAX_SCAN_CHARS):
     """Resolve every cross-link in ``bundle`` against the concepts it contains.
 
     ``bundle`` maps concept path to document text (as :func:`import_bundle`). Only
     the body is scanned for links. See :class:`LinkGraphResult` for the outcome.
+
+    Self-safety (OWASP LLM10): every body is attacker-supplied and each is walked
+    by a `findall`, so each body is capped at ``max_scan_chars`` and recorded in
+    ``truncated``. It truncates rather than raising, the way the scanners do: the
+    graph reports on documents, it does not hand them back, so a shortened scan
+    costs edges — not the caller's content.
     """
     present = {p[: -len(".md")] for p in bundle if p.endswith(".md")}
-    dangling, rejected, resolved = [], [], []
+    dangling, rejected, resolved, truncated = [], [], [], []
 
     for path in sorted(bundle):
         if not path.endswith(".md"):
@@ -493,6 +503,10 @@ def link_graph(bundle):
         except OKFFrontmatterError:
             body = bundle[path]  # unparseable frontmatter is T2's reject, not ours
 
+        if len(body) > max_scan_chars:
+            truncated.append((from_id, len(body)))
+            body = body[:max_scan_chars]
+
         for target in extract_link_targets(body):
             try:
                 concept_id = resolve_link(target, from_id)
@@ -506,7 +520,9 @@ def link_graph(bundle):
             else:
                 dangling.append((from_id, concept_id))
 
-    return LinkGraphResult(tuple(dangling), tuple(rejected), tuple(resolved))
+    return LinkGraphResult(
+        tuple(dangling), tuple(rejected), tuple(resolved), tuple(truncated)
+    )
 
 
 def _normalize_bundle_path(path):

src/llm_ingestion_guard/output.py

@@ -336,6 +336,7 @@ def scan_output(
     # 6. Active-content constructs with an external target (the EchoLeak class,
     #    OWASP LLM05) — reported here so disposition sees them; defanging stays
     #    neutralize's separate, opt-in job.
-    report.extend(scan_active_content(scan_text, source).findings)
+    #    scan_text is already <= cap, so no second oversize finding is emitted.
+    report.extend(scan_active_content(scan_text, source, max_scan_chars).findings)
 
     return report

tests/test_active_content.py

@@ -331,3 +331,30 @@ def test_url_defanging_survives_the_redos_fix():
         evidence = " ".join(f.evidence or "" for f in report.findings)
         assert expected in evidence, raw
         assert "http://" not in evidence and "https://" not in evidence, raw
+
+
+# --- self-safety (OWASP LLM10) ----------------------------------------------
+#
+# Reached through `scan_output` this detector inherits that surface's cap. Called
+# directly — the shape an adapter reaches for when it wants the active-content
+# classes alone — it had none. It is detection-shaped, so it truncates and flags
+# rather than raising the way the transform surfaces do: what a shortened scan
+# costs is coverage of the tail, not the caller's content.
+
+def test_oversize_input_is_capped_and_flagged():
+    big = "x" * 200 + "\n![alt](https://evil.example/beyond-the-cap)\n"
+    report = scan_active_content(big, max_scan_chars=50)
+
+    oversize = [f for f in report.findings if "oversize" in f.label]
+    assert len(oversize) == 1
+    assert oversize[0].owasp == "LLM10"
+    assert oversize[0].count == len(big)
+    # Prefix only: the construct past the cap is not reported. This is the cost
+    # the flag exists to announce, so assert it rather than assume it.
+    assert not [f for f in report.findings if f.label == "active:markdown-image"]
+
+
+def test_input_exactly_at_the_cap_is_not_flagged():
+    # The cap is the largest scanned size, not the smallest truncated one.
+    report = scan_active_content("x" * 50, max_scan_chars=50)
+    assert not [f for f in report.findings if "oversize" in f.label]

tests/test_okf.py

@@ -496,6 +496,26 @@ def test_link_graph_resolves_present_target():
     assert graph.dangling == ()
 
 
+def test_link_graph_caps_an_oversize_body_and_records_it():
+    # Self-safety (OWASP LLM10): the graph runs a `findall` over every body in
+    # the bundle, all of it attacker-supplied. It is detection-shaped, so it
+    # truncates and records rather than raising — the caller's documents are not
+    # what it returns.
+    body = "y" * 200 + "\nSee [later](/b/target.md).\n"
+    graph = link_graph({"a/main.md": "---\ntype: t\n---\n" + body}, max_scan_chars=50)
+
+    assert graph.truncated == (("a/main", len(body)),)
+    # The link past the cap was never read — that cost is what the record announces.
+    assert graph.dangling == ()
+
+
+def test_link_graph_body_at_the_cap_is_not_recorded():
+    body = "See [later](/b/target.md).\n"
+    graph = link_graph({"a/main.md": "---\ntype: t\n---\n" + body}, max_scan_chars=len(body))
+    assert graph.truncated == ()
+    assert ("a/main", "b/target") in graph.dangling
+
+
 def test_link_graph_records_rejected_dangerous_link():
     bundle = {"a/main.md": "---\ntype: t\n---\n[x](javascript:alert(1))\n"}
     graph = link_graph(bundle)