Skip to content
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.

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

vmray: record command line info #2515

Merged
merged 3 commits into from
Dec 3, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@

- allow call as valid subscope for call scoped rules @mr-tz
- support loading and analyzing a Binary Ninja database #2496 @xusheng6
- vmray: record process command line details @mr-tz

### Breaking Changes

Expand Down
11 changes: 10 additions & 1 deletion capa/features/extractors/vmray/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -35,6 +35,8 @@ class VMRayMonitorProcess:
ppid: int # parent process ID assigned by OS
monitor_id: int # unique ID assigned to process by VMRay
image_name: str
filename: str
cmd_line: str


class VMRayAnalysis:
Expand Down Expand Up @@ -160,7 +162,12 @@ def _compute_monitor_processes(self):
self.sv2.processes[process.ref_parent_process.path[1]].os_pid if process.ref_parent_process else 0
)
self.monitor_processes[process.monitor_id] = VMRayMonitorProcess(
process.os_pid, ppid, process.monitor_id, process.image_name
process.os_pid,
ppid,
process.monitor_id,
process.image_name,
process.filename,
process.cmd_line,
)

# not all processes are recorded in SummaryV2.json, get missing data from flog.xml, see #2394
Expand All @@ -170,6 +177,8 @@ def _compute_monitor_processes(self):
monitor_process.os_parent_pid,
monitor_process.process_id,
monitor_process.image_name,
monitor_process.filename,
monitor_process.cmd_line,
)

if monitor_process.process_id not in self.monitor_processes:
Expand Down
2 changes: 1 addition & 1 deletion capa/features/extractors/vmray/extractor.py
Original file line number Diff line number Diff line change
Expand Up @@ -86,7 +86,7 @@ def extract_process_features(self, ph: ProcessHandle) -> Iterator[tuple[Feature,

def get_process_name(self, ph) -> str:
monitor_process: VMRayMonitorProcess = ph.inner
return monitor_process.image_name
return f"{monitor_process.image_name} ({monitor_process.cmd_line})"

def get_threads(self, ph: ProcessHandle) -> Iterator[ThreadHandle]:
for monitor_thread_id in self.analysis.monitor_threads_by_monitor_process[ph.inner.monitor_id]:
Expand Down
16 changes: 13 additions & 3 deletions capa/features/extractors/vmray/models.py
Original file line number Diff line number Diff line change
Expand Up @@ -136,19 +136,28 @@ class FunctionReturn(BaseModel):
from_addr: HexInt = Field(alias="from")


def sanitize_string(value: str) -> str:
# e.g. "cmd_line": "\"C:\\Users\\38lTTV5Kii\\Desktop\\filename.exe\" ",
return value.replace("\\\\", "\\").strip(' "')
williballenthin marked this conversation as resolved.
Show resolved Hide resolved


# unify representation
SanitizedString = Annotated[str, BeforeValidator(sanitize_string)]


class MonitorProcess(BaseModel):
ts: HexInt
process_id: int
image_name: str
filename: str
filename: SanitizedString
# page_root: HexInt
os_pid: HexInt
# os_integrity_level: HexInt
# os_privileges: HexInt
monitor_reason: str
parent_id: int
os_parent_pid: HexInt
# cmd_line: str
cmd_line: SanitizedString
# cur_dir: str
# os_username: str
# bitness: int
Expand Down Expand Up @@ -306,8 +315,9 @@ class Process(BaseModel):
monitor_id: int
# monitor_reason: str
os_pid: int
filename: str
filename: SanitizedString
image_name: str
cmd_line: SanitizedString
ref_parent_process: Optional[GenericReference] = None


Expand Down
Loading