From 6cef1d59f0ea06874db65ecc2e74d6f513aeb0f7 Mon Sep 17 00:00:00 2001
From: test-user <kuznetsov.va@gmail.com>
Date: Sun, 24 May 2026 15:55:07 -0700
Subject: [PATCH] fix(c2pa): drop non-printable claim_generator garbage

On some manifests (observed: Microsoft Designer) the first CBOR "name"
key precedes a binary hash field, not the generator string, so
_cbor_text_after returns control-char garbage. Guard with isprintable()
to drop it; issuer detection (byte-search) and the SynthID verdict are
unaffected. Adds TestParseChunkGuards covering kept-vs-dropped cases.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 src/remove_ai_watermarks/noai/c2pa.py |  7 +++++--
 tests/test_noai.py                    | 27 +++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/src/remove_ai_watermarks/noai/c2pa.py b/src/remove_ai_watermarks/noai/c2pa.py
index 08d61bc..f3ef4a7 100644
--- a/src/remove_ai_watermarks/noai/c2pa.py
+++ b/src/remove_ai_watermarks/noai/c2pa.py
@@ -196,9 +196,12 @@ def _parse_c2pa_chunk(chunk_data: bytes, c2pa_info: dict[str, Any]) -> None:
 
     # Claim generator and spec version: read the CBOR text-string values
     # directly (regex byte-grabbing produced artifacts like ``fGPT-4o``).
-    if generator := _cbor_text_after(chunk_data, b"name"):
+    # Guard with isprintable(): on some manifests (e.g. Microsoft Designer) the
+    # first ``name`` key precedes a binary field (a hash), not the generator
+    # string, which would otherwise surface as control-char garbage.
+    if (generator := _cbor_text_after(chunk_data, b"name")) and generator.isprintable():
         c2pa_info["claim_generator"] = generator
-    if spec := _cbor_text_after(chunk_data, b"specVersion"):
+    if (spec := _cbor_text_after(chunk_data, b"specVersion")) and spec.isprintable():
         c2pa_info["c2pa_spec"] = spec
 
     # Find actions
diff --git a/tests/test_noai.py b/tests/test_noai.py
index 1665040..ad59699 100644
--- a/tests/test_noai.py
+++ b/tests/test_noai.py
@@ -9,6 +9,7 @@ import pytest
 
 from remove_ai_watermarks.noai.c2pa import (
     _cbor_text_after,
+    _parse_c2pa_chunk,
     extract_c2pa_chunk,
     extract_c2pa_info,
     has_c2pa_metadata,
@@ -232,6 +233,32 @@ class TestSynthIDVerdict:
         assert "Google LLC, OpenAI" in synthid_verdict("Google LLC, OpenAI")
 
 
+class TestParseChunkGuards:
+    """_parse_c2pa_chunk rejects non-printable claim_generator garbage.
+
+    On some manifests (observed: Microsoft Designer) the first ``name`` key
+    precedes a binary hash field, not the generator string. The clean issuer +
+    SynthID verdict must still come through.
+    """
+
+    def test_clean_generator_kept(self):
+        # "name" + CBOR text-string (head 0x69 = 0x60+9) "gpt-image"
+        chunk = b"...name" + bytes([0x69]) + b"gpt-image" + b"OpenAI trainedAlgorithmicMedia"
+        info: dict = {}
+        _parse_c2pa_chunk(chunk, info)
+        assert info["claim_generator"] == "gpt-image"
+        assert "OpenAI" in info["issuer"]
+        assert "synthid_watermark" in info  # OpenAI + trainedAlgorithmicMedia
+
+    def test_nonprintable_generator_dropped(self):
+        # "name" + CBOR string (head 0x64 = len 4) with a control byte -> garbage
+        chunk = b"...name" + bytes([0x64]) + b"\x81abc" + b"OpenAI trainedAlgorithmicMedia"
+        info: dict = {}
+        _parse_c2pa_chunk(chunk, info)
+        assert "claim_generator" not in info  # control-char garbage rejected
+        assert "OpenAI" in info["issuer"]  # issuer byte-search still robust
+
+
 # ── ISOBMFF (AVIF / HEIF / JPEG-XL container stripping) ──────────────
 
 FTYP = b"\x00\x00\x00\x18ftypavif\x00\x00\x00\x00avifmif1"  # 24-byte ftyp box