Stowage/clamav
2
0
Fork 0
mirror of https://github.com/Cisco-Talos/clamav.git synced 2025-12-08 06:09:46 +00:00
Code Issues Projects Releases Packages Wiki Activity
clamav/sigtool/vba.h

32 lines
1 KiB
C
Raw Normal View History

Tue Dec 14 11:15:22 GMT 2004 (trog) ----------------------------------- * sigtool/options.c sigtool/sigtool.c: New options: --vba and --vba-hex * sigtool/vba.c sigtool/vba.h: New files. Code to extract VBA/Word6 macros git-svn: trunk@1183
2004-12-14 11:20:01 +00:00
/*
* Copyright (C) 2004 Trog <trog@uncon.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
update GPL headers with new address for FSF git-svn: trunk@1901
2006-04-09 19:59:28 +00:00
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
* MA 02110-1301, USA.
Tue Dec 14 11:15:22 GMT 2004 (trog) ----------------------------------- * sigtool/options.c sigtool/sigtool.c: New options: --vba and --vba-hex * sigtool/vba.c sigtool/vba.h: New files. Code to extract VBA/Word6 macros git-svn: trunk@1183
2004-12-14 11:20:01 +00:00
*/
clang-format'd using new .clang-format rules.
2018-12-03 12:40:13 -05:00
Tue Dec 14 11:15:22 GMT 2004 (trog) ----------------------------------- * sigtool/options.c sigtool/sigtool.c: New options: --vba and --vba-hex * sigtool/vba.c sigtool/vba.h: New files. Code to extract VBA/Word6 macros git-svn: trunk@1183
2004-12-14 11:20:01 +00:00
#ifndef __VBA_H
#define __VBA_H
Add CMake build tooling This patch adds experimental-quality CMake build tooling. The libmspack build required a modification to use "" instead of <> for header #includes. This will hopefully be included in the libmspack upstream project when adding CMake build tooling to libmspack. Removed use of libltdl when using CMake. Flex & Bison are now required to build. If -DMAINTAINER_MODE, then GPERF is also required, though it currently doesn't actually do anything. TODO! I found that the autotools build system was generating the lexer output but not actually compiling it, instead using previously generated (and manually renamed) lexer c source. As a consequence, changes to the .l and .y files weren't making it into the build. To resolve this, I removed generated flex/bison files and fixed the tooling to use the freshly generated files. Flex and bison are now required build tools. On Windows, this adds a dependency on the winflexbison package, which can be obtained using Chocolatey or may be manually installed. CMake tooling only has partial support for building with external LLVM library, and no support for the internal LLVM (to be removed in the future). I.e. The CMake build currently only supports the bytecode interpreter. Many files used include paths relative to the top source directory or relative to the current project, rather than relative to each build target. Modern CMake support requires including internal dependency headers the same way you would external dependency headers (albeit with "" instead of <>). This meant correcting all header includes to be relative to the build targets and not relative to the workspace. For example, ... ```c include "../libclamav/clamav.h" include "clamd/clamd_others.h" ``` ... becomes: ```c // libclamav include "clamav.h" // clamd include "clamd_others.h" ``` Fixes header name conflicts by renaming a few of the files. Converted the "shared" code into a static library, which depends on libclamav. The ironically named "shared" static library provides features common to the ClamAV apps which are not required in libclamav itself and are not intended for use by downstream projects. This change was required for correct modern CMake practices but was also required to use the automake "subdir-objects" option. This eliminates warnings when running autoreconf which, in the next version of autoconf & automake are likely to break the build. libclamav used to build in multiple stages where an earlier stage is a static library containing utils required by the "shared" code. Linking clamdscan and clamdtop with this libclamav utils static lib allowed these two apps to function without libclamav. While this is nice in theory, the practical gains are minimal and it complicates the build system. As such, the autotools and CMake tooling was simplified for improved maintainability and this feature was thrown out. clamdtop and clamdscan now require libclamav to function. Removed the nopthreads version of the autotools libclamav_internal_utils static library and added pthread linking to a couple apps that may have issues building on some platforms without it, with the intention of removing needless complexity from the source. Kept the regular version of libclamav_internal_utils.la though it is no longer used anywhere but in libclamav. Added an experimental doxygen build option which attempts to build clamav.h and libfreshclam doxygen html docs. The CMake build tooling also may build the example program(s), which isn't a feature in the Autotools build system. Changed C standard to C90+ due to inline linking issues with socket.h when linking libfreshclam.so on Linux. Generate common.rc for win32. Fix tabs/spaces in shared Makefile.am, and remove vestigial ifndef from misc.c. Add CMake files to the automake dist, so users can try the new CMake tooling w/out having to build from a git clone. clamonacc changes: - Renamed FANOTIFY macro to HAVE_SYS_FANOTIFY_H to better match other similar macros. - Added a new clamav-clamonacc.service systemd unit file, based on the work of ChadDevOps & Aaron Brighton. - Added missing clamonacc man page. Updates to clamdscan man page, add missing options. Remove vestigial CL_NOLIBCLAMAV definitions (all apps now use libclamav). Rename Windows mspack.dll to libmspack.dll so all ClamAV-built libraries have the lib-prefix with Visual Studio as with CMake.
2020-08-13 00:25:34 -07:00
// libclamav
#include "uniq.h"
#include "others.h"
fix fmap stuff in sigtool
2010-02-10 17:53:27 +01:00
improve handling of PDF, CAB, RTF, OLE2 and HTML files (sync with branch/0.93) git-svn: trunk@3862
2008-05-27 16:30:47 +00:00
int sigtool_vba_scandir(const char *dirname, int hex_output, struct uniq *U);
fix fmap stuff in sigtool
2010-02-10 17:53:27 +01:00
cli_ctx *convenience_ctx(int fd);
libclamav: Fix scan recursion tracking Scan recursion is the process of identifying files embedded in other files and then scanning them, recursively. Internally this process is more complex than it may sound because a file may have multiple layers of types before finding a new "file". At present we treat the recursion count in the scanning context as an index into both our fmap list AND our container list. These two lists are conceptually a part of the same thing and should be unified. But what's concerning is that the "recursion level" isn't actually incremented or decremented at the same time that we add a layer to the fmap or container lists but instead is more touchy-feely, increasing when we find a new "file". To account for this shadiness, the size of the fmap and container lists has always been a little longer than our "max scan recursion" limit so we don't accidentally overflow the fmap or container arrays (!). I've implemented a single recursion-stack as an array, similar to before, which includes a pointer to each fmap at each layer, along with the size and type. Push and pop functions add and remove layers whenever a new fmap is added. A boolean argument when pushing indicates if the new layer represents a new buffer or new file (descriptor). A new buffer will reset the "nested fmap level" (described below). This commit also provides a solution for an issue where we detect embedded files more than once during scan recursion. For illustration, imagine a tarball named foo.tar.gz with this structure: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | foo.tar.gz | GZ | 0 | 0 | | └── foo.tar | TAR | 1 | 0 | | ├── bar.zip | ZIP | 2 | 1 | | │   └── hola.txt | ASCII | 3 | 0 | | └── baz.exe | PE | 2 | 1 | But suppose baz.exe embeds a ZIP archive and a 7Z archive, like this: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | baz.exe | PE | 0 | 0 | | ├── sfx.zip | ZIP | 1 | 1 | | │   └── hello.txt | ASCII | 2 | 0 | | └── sfx.7z | 7Z | 1 | 1 | |    └── world.txt | ASCII | 2 | 0 | (A) If we scan for embedded files at any layer, we may detect: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | foo.tar.gz | GZ | 0 | 0 | | ├── foo.tar | TAR | 1 | 0 | | │ ├── bar.zip | ZIP | 2 | 1 | | │ │   └── hola.txt | ASCII | 3 | 0 | | │ ├── baz.exe | PE | 2 | 1 | | │ │ ├── sfx.zip | ZIP | 3 | 1 | | │ │ │   └── hello.txt | ASCII | 4 | 0 | | │ │ └── sfx.7z | 7Z | 3 | 1 | | │ │    └── world.txt | ASCII | 4 | 0 | | │ ├── sfx.zip | ZIP | 2 | 1 | | │ │   └── hello.txt | ASCII | 3 | 0 | | │ └── sfx.7z | 7Z | 2 | 1 | | │   └── world.txt | ASCII | 3 | 0 | | ├── sfx.zip | ZIP | 1 | 1 | | └── sfx.7z | 7Z | 1 | 1 | (A) is bad because it scans content more than once. Note that for the GZ layer, it may detect the ZIP and 7Z if the signature hits on the compressed data, which it might, though extracting the ZIP and 7Z will likely fail. The reason the above doesn't happen now is that we restrict embedded type scans for a bunch of archive formats to include GZ and TAR. (B) If we scan for embedded files at the foo.tar layer, we may detect: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | foo.tar.gz | GZ | 0 | 0 | | └── foo.tar | TAR | 1 | 0 | | ├── bar.zip | ZIP | 2 | 1 | | │   └── hola.txt | ASCII | 3 | 0 | | ├── baz.exe | PE | 2 | 1 | | ├── sfx.zip | ZIP | 2 | 1 | | │   └── hello.txt | ASCII | 3 | 0 | | └── sfx.7z | 7Z | 2 | 1 | |    └── world.txt | ASCII | 3 | 0 | (B) is almost right. But we can achieve it easily enough only scanning for embedded content in the current fmap when the "nested fmap level" is 0. The upside is that it should safely detect all embedded content, even if it may think the sfz.zip and sfx.7z are in foo.tar instead of in baz.exe. The biggest risk I can think of affects ZIPs. SFXZIP detection is identical to ZIP detection, which is why we don't allow SFXZIP to be detected if insize of a ZIP. If we only allow embedded type scanning at fmap-layer 0 in each buffer, this will fail to detect the embedded ZIP if the bar.exe was not compressed in foo.zip and if non-compressed files extracted from ZIPs aren't extracted as new buffers: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | foo.zip | ZIP | 0 | 0 | | └── bar.exe | PE | 1 | 1 | | └── sfx.zip | ZIP | 2 | 2 | Provided that we ensure all files extracted from zips are scanned in new buffers, option (B) should be safe. (C) If we scan for embedded files at the baz.exe layer, we may detect: | description | type | rec level | nested fmap level | | ------------------------- | ----- | --------- | ----------------- | | foo.tar.gz | GZ | 0 | 0 | | └── foo.tar | TAR | 1 | 0 | | ├── bar.zip | ZIP | 2 | 1 | | │   └── hola.txt | ASCII | 3 | 0 | | └── baz.exe | PE | 2 | 1 | | ├── sfx.zip | ZIP | 3 | 1 | | │   └── hello.txt | ASCII | 4 | 0 | | └── sfx.7z | 7Z | 3 | 1 | |    └── world.txt | ASCII | 4 | 0 | (C) is right. But it's harder to achieve. For this example we can get it by restricting 7ZSFX and ZIPSFX detection only when scanning an executable. But that may mean losing detection of archives embedded elsewhere. And we'd have to identify allowable container types for each possible embedded type, which would be very difficult. So this commit aims to solve the issue the (B)-way. Note that in all situations, we still have to scan with file typing enabled to determine if we need to reassign the current file type, such as re-identifying a Bzip2 archive as a DMG that happens to be Bzip2- compressed. Detection of DMG and a handful of other types rely on finding data partway through or near the ned of a file before reassigning the entire file as the new type. Other fixes and considerations in this commit: - The utf16 HTML parser has weak error handling, particularly with respect to creating a nested fmap for scanning the ascii decoded file. This commit cleans up the error handling and wraps the nested scan with the recursion-stack push()/pop() for correct recursion tracking. Before this commit, each container layer had a flag to indicate if the container layer is valid. We need something similar so that the cli_recursion_stack_get_*() functions ignore normalized layers. Details... Imagine an LDB signature for HTML content that specifies a ZIP container. If the signature actually alerts on the normalized HTML and you don't ignore normalized layers for the container check, it will appear as though the alert is in an HTML container rather than a ZIP container. This commit accomplishes this with a boolean you set in the scan context before scanning a new layer. Then when the new fmap is created, it will use that flag to set similar flag for the layer. The context flag is reset those that anything after this doesn't have that flag. The flag allows the new recursion_stack_get() function to ignore normalized layers when iterating the stack to return a layer at a requested index, negative or positive. Scanning normalized extracted/normalized javascript and VBA should also use the 'layer is normalized' flag. - This commit also fixes Heuristic.Broken.Executable alert for ELF files to make sure that: A) these only alert if cli_append_virus() returns CL_VIRUS (aka it respects the FP check). B) all broken-executable alerts for ELF only happen if the SCAN_HEURISTIC_BROKEN option is enabled. - This commit also cleans up the error handling in cli_magic_scan_dir(). This was needed so we could correctly apply the layer-is-normalized-flag to all VBA macros extracted to a directory when scanning the directory. - Also fix an issue where exceeding scan maximums wouldn't cause embedded file detection scans to abort. Granted we don't actually want to abort if max filesize or max recursion depth are exceeded... only if max scansize, max files, and max scantime are exceeded. Add 'abort_scan' flag to scan context, to protect against depending on correct error propagation for fatal conditions. Instead, setting this flag in the scan context should guarantee that a fatal condition deep in scan recursion isn't lost which result in more stuff being scanned instead of aborting. This shouldn't be necessary, but some status codes like CL_ETIMEOUT never used to be fatal and it's easier to do this than to verify every parser only returns CL_ETIMEOUT and other "fatal status codes" in fatal conditions. - Remove duplicate is_tar() prototype from filestypes.c and include is_tar.h instead. - Presently we create the fmap hash when creating the fmap. This wastes a bit of CPU if the hash is never needed. Now that we're creating fmap's for all embedded files discovered with file type recognition scans, this is a much more frequent occurence and really slows things down. This commit fixes the issue by only creating fmap hashes as needed. This should not only resolve the perfomance impact of creating fmap's for all embedded files, but also should improve performance in general. - Add allmatch check to the zip parser after the central-header meta match. That way we don't multiple alerts with the same match except in allmatch mode. Clean up error handling in the zip parser a tiny bit. - Fixes to ensure that the scan limits such as scansize, filesize, recursion depth, # of embedded files, and scantime are always reported if AlertExceedsMax (--alert-exceeds-max) is enabled. - Fixed an issue where non-fatal alerts for exceeding scan maximums may mask signature matches later on. I changed it so these alerts use the "possibly unwanted" alert-type and thus only alert if no other alerts were found or if all-match or heuristic-precedence are enabled. - Added the "Heuristics.Limits.Exceeded.*" events to the JSON metadata when the --gen-json feature is enabled. These will show up once under "ParseErrors" the first time a limit is exceeded. In the present implementation, only one limits-exceeded events will be added, so as to prevent a malicious or malformed sample from filling the JSON buffer with millions of events and using a tonne of RAM.
2021-09-11 14:15:21 -07:00
void destroy_ctx(cli_ctx *ctx);
Tue Dec 14 11:15:22 GMT 2004 (trog) ----------------------------------- * sigtool/options.c sigtool/sigtool.c: New options: --vba and --vba-hex * sigtool/vba.c sigtool/vba.h: New files. Code to extract VBA/Word6 macros git-svn: trunk@1183
2004-12-14 11:20:01 +00:00
#endif
Reference in a new issue Copy permalink