From d6b3fb96718ff16c2e1bd2a5eb0526ec6e2cffd7 Mon Sep 17 00:00:00 2001
From: "Dylan M. Taylor" <dylan@dylanmtaylor.com>
Date: Fri, 23 Oct 2026 21:54:26 -0400
Subject: [PATCH] security: bound vendored hayro ASCII85 output by the stream
 decode limit (#253)

* security: bound ASCII85 output by the stream decode limit (CodeRabbit)

* fix(ascii85): truncate terminal partial groups to decode limit
---
 vendor/hayro-syntax/src/filter/ascii_85.rs | 28 ++++++++++++++++++++--
 vendor/hayro-syntax/src/filter/mod.rs      |  2 +-
 2 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/vendor/hayro-syntax/src/filter/ascii_85.rs b/vendor/hayro-syntax/src/filter/ascii_85.rs
index 5a18cf83..b7199365 100644
--- a/vendor/hayro-syntax/src/filter/ascii_85.rs
+++ b/vendor/hayro-syntax/src/filter/ascii_85.rs
@@ -4,7 +4,9 @@ use crate::reader::Reader;
 use crate::trivia::is_white_space_character;
 use alloc::vec::Vec;
 
-pub(crate) fn decode(data: &[u8]) -> Option<Vec<u8>> {
+/// PdfCraft patch: `limit` is the most bytes produced (see `filter::decode_limit`); each `z` costs
+/// one input byte and yields four, so a Flate stream of them would outgrow the budget.
+pub(crate) fn decode(data: &[u8], limit: usize) -> Option<Vec<u8>> {
     const POW_85: [u32; 5] = [52200625, 614125, 7225, 85, 1];
 
     let mut reader = Reader::new(data);
@@ -55,13 +57,21 @@ pub(crate) fn decode(data: &[u8]) -> Option<Vec<u8>> {
         Some(())
     };
 
-    let mut decoded = Vec::with_capacity(data.len() * 4 / 5);
+    let mut decoded = Vec::with_capacity((data.len() * 4 / 5).min(limit));
     let mut group = Vec::with_capacity(5);
 
     loop {
+        if decoded.len() >= limit {
+            decoded.truncate(limit);
+            warn!("ascii85 stream stopped at its decode limit of {limit} bytes");
+
+            return Some(decoded);
+        }
+
         let Some(b) = read_byte() else {
             // Be lenient and accept what we have (see PDFBOX-5910).
             flush_group(&mut group, &mut decoded)?;
+            decoded.truncate(limit);
 
             return Some(decoded);
         };
@@ -82,6 +92,7 @@ pub(crate) fn decode(data: &[u8]) -> Option<Vec<u8>> {
                 // Technically requires a '>', but there is a PDF where it isn't
                 // appended and decodes fine in other viewers.
                 flush_group(&mut group, &mut decoded)?;
+                decoded.truncate(limit);
 
                 return Some(decoded);
             }
@@ -89,3 +100,16 @@ pub(crate) fn decode(data: &[u8]) -> Option<Vec<u8>> {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::decode;
+
+    #[test]
+    fn output_stops_at_the_limit() {
+        assert_eq!(decode(&[b'z'; 100], 10).unwrap().len(), 10);
+        assert_eq!(decode(b"zz~>", 100).unwrap(), [0; 8]);
+        assert_eq!(decode(b"!!!!~>", 2).unwrap().len(), 2);
+        assert_eq!(decode(b"!!!!", 2).unwrap().len(), 2);
+    }
+}
diff --git a/vendor/hayro-syntax/src/filter/mod.rs b/vendor/hayro-syntax/src/filter/mod.rs
index 90ffd76e..e3622795 100644
--- a/vendor/hayro-syntax/src/filter/mod.rs
+++ b/vendor/hayro-syntax/src/filter/mod.rs
@@ -95,7 +95,7 @@ impl Filter {
             Self::AsciiHexDecode => ascii_hex::decode(data)
                 .map(FilterResult::from_data)
                 .ok_or(DecodeFailure::StreamDecode),
-            Self::Ascii85Decode => ascii_85::decode(data)
+            Self::Ascii85Decode => ascii_85::decode(data, limit)
                 .map(FilterResult::from_data)
                 .ok_or(DecodeFailure::StreamDecode),
             Self::RunLengthDecode => run_length::decode(data, limit)