Skip to content

cpp: model Protocol Buffers parse/serialize taint flow #22448

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jketema merged 5 commits into from
Sep 12, 2026
Merged

cpp: model Protocol Buffers parse/serialize taint flow #22448

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9c85aab
cpp: model Protocol Buffers parse/serialize taint flow
kumarak Aug 27, 2026
a7e2584
Update cpp/ql/lib/change-notes/2026-08-27-protobuf-models.md
kumarak Aug 28, 2026
d84a302
fix(cpp): correct protobuf string parse models and expand test coverage
kumarak Aug 28, 2026
d603cdd
test(cpp): add sink-based protobuf model tests and trim comments
kumarak Sep 3, 2026
d293e87
test(cpp): fix protobuf model CI failures
kumarak Sep 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions cpp/ql/lib/change-notes/2026-08-27-protobuf-models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
---
category: minorAnalysis
---
* Added flow summaries for the Protocol Buffers `google::protobuf::MessageLite` C++ API.
59 changes: 59 additions & 0 deletions cpp/ql/lib/ext/Protobuf.model.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
extensions:
- addsTo:
pack: codeql/cpp-all
extensible: summaryModel
data: # namespace, type, subtypes, name, signature, ext, input, output, kind, provenance
# File-descriptor variants (`{Parse,Serialize}*FromFileDescriptor`) are intentionally omitted:
# the descriptor is an `int`, not a data buffer, so there is no buffer argument to model.

# Deserialization
- ["google::protobuf", "MessageLite", True, "ParseFromString", "(string_view)", "", "Argument[0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromString", "(const Cord &)", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromString", "(string_view)", "", "Argument[0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromString", "(const Cord &)", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergeFromString", "(string_view)", "", "Argument[0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergeFromString", "(const Cord &)", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergePartialFromString", "(string_view)", "", "Argument[0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergePartialFromString", "(const Cord &)", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromArray", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromArray", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromCord", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromCord", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergeFromCord", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergePartialFromCord", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromIstream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromIstream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromBoundedZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromBoundedZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergeFromBoundedZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
Comment on lines +26 to +30
- ["google::protobuf", "MessageLite", True, "MergePartialFromBoundedZeroCopyStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParseFromCodedStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "ParsePartialFromCodedStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergeFromCodedStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "MergePartialFromCodedStream", "", "", "Argument[*0]", "Argument[-1]", "taint", "manual"]

# Serialization
- ["google::protobuf", "MessageLite", True, "SerializeToString", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToString", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "AppendToString", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "AppendPartialToString", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeToArray", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToArray", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeToCord", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToCord", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "AppendToCord", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "AppendPartialToCord", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeToOstream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToOstream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeToZeroCopyStream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToZeroCopyStream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeToCodedStream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialToCodedStream", "", "", "Argument[-1]", "Argument[*0]", "taint", "manual"]

# Serialization returning bytes
- ["google::protobuf", "MessageLite", True, "SerializeAsString", "", "", "Argument[-1]", "ReturnValue", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialAsString", "", "", "Argument[-1]", "ReturnValue", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializeAsCord", "", "", "Argument[-1]", "ReturnValue", "taint", "manual"]
- ["google::protobuf", "MessageLite", True, "SerializePartialAsCord", "", "", "Argument[-1]", "ReturnValue", "taint", "manual"]
19 changes: 3 additions & 16 deletions cpp/ql/test/library-tests/dataflow/external-models/asio_streams.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,24 +1,11 @@

// --- stub library headers ---

namespace std {
typedef unsigned long size_t;
#define SIZE_MAX 0xFFFFFFFF
#include "std_string.h"

template <class T> class allocator {
};

template<class charT> struct char_traits {
};

template<class charT, class traits = char_traits<charT>, class Allocator = allocator<charT> >
class basic_string {
public:
basic_string(const charT* s, const Allocator& a = Allocator());
};

typedef basic_string<char> string;
#define SIZE_MAX 0xFFFFFFFF

namespace std {
class string_view {
public:
string_view(const char* s);
Expand Down
Loading
Loading