py/tarslip: detect shutil.unpack_archive and subprocess tar extraction #21720
+59
−0
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -132,6 +132,79 @@ module TarSlip { | |
| } | ||
| } | ||
|
|
||
| /** | ||
| * A call to `shutil.unpack_archive`, considered as a flow source. | ||
| * | ||
| * The archive filename is not hardcoded, so it may come from user input. | ||
| */ | ||
| class ShutilUnpackArchiveSource extends Source { | ||
| ShutilUnpackArchiveSource() { | ||
| this = API::moduleImport("shutil").getMember("unpack_archive").getACall() and | ||
| not this.(DataFlow::CallCfgNode).getArg(0).getALocalSource().asExpr() instanceof StringLiteral | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * A call to `shutil.unpack_archive`, considered as a flow sink. | ||
| * | ||
| * The archive filename is not hardcoded, so it may come from user input. | ||
| */ | ||
| class ShutilUnpackArchiveSink extends Sink { | ||
| ShutilUnpackArchiveSink() { | ||
| this = API::moduleImport("shutil").getMember("unpack_archive").getACall() and | ||
| not this.(DataFlow::CallCfgNode).getArg(0).getALocalSource().asExpr() instanceof StringLiteral | ||
|
Contributor
There was a problem hiding this comment. Remove this line, not really needed.
Contributor
Author
There was a problem hiding this comment. Done in 5084883 — changed |
||
| } | ||
| } | ||
|
|
||
| /** | ||
| * Holds if `call` is a subprocess call that invokes `tar` for archive extraction | ||
| * with at least one non-literal argument (the archive filename). | ||
| * | ||
| * Detects patterns like `subprocess.run(["tar", "-xf", untrusted_filename])`. | ||
| */ | ||
| private predicate isSubprocessTarExtraction(DataFlow::CallCfgNode call) { | ||
| exists(SequenceNode cmdList | | ||
| call = | ||
| API::moduleImport("subprocess") | ||
| .getMember(["run", "call", "check_call", "check_output", "Popen"]) | ||
| .getACall() and | ||
| cmdList = call.getArg(0).asCfgNode() and | ||
| // Command must be "tar" exactly or a path ending in "/tar" (e.g. "/usr/bin/tar") | ||
| exists(string cmd | | ||
| cmd = cmdList.getElement(0).getNode().(StringLiteral).getText() and | ||
| (cmd = "tar" or cmd.matches("%/tar")) | ||
| ) and | ||
| // At least one extraction-related flag must be present: | ||
| // single-dash flags containing 'x' (like -x, -xf, -xvf) or the long option --extract | ||
| exists(string flag | | ||
| flag = cmdList.getElement(_).getNode().(StringLiteral).getText() and | ||
| (flag.regexpMatch("-[a-zA-Z]*x[a-zA-Z]*") or flag = "--extract") | ||
| ) and | ||
| // At least one non-literal argument (the archive filename) | ||
| exists(int i | | ||
| i > 0 and | ||
| exists(cmdList.getElement(i)) and | ||
| not cmdList.getElement(i).getNode() instanceof StringLiteral | ||
| ) | ||
| ) | ||
| } | ||
|
|
||
| /** | ||
| * A call to `subprocess` functions that invokes `tar` for archive extraction, | ||
| * considered as a flow source. | ||
| */ | ||
| class SubprocessTarExtractionSource extends Source { | ||
|
Contributor
There was a problem hiding this comment. Remove (should not be a source).
Contributor
Author
There was a problem hiding this comment. Done in 5084883 — |
||
| SubprocessTarExtractionSource() { isSubprocessTarExtraction(this) } | ||
| } | ||
|
|
||
| /** | ||
| * A call to `subprocess` functions that invokes `tar` for archive extraction, | ||
| * considered as a flow sink. | ||
| */ | ||
| class SubprocessTarExtractionSink extends Sink { | ||
| SubprocessTarExtractionSink() { isSubprocessTarExtraction(this) } | ||
|
Contributor
There was a problem hiding this comment. It should not be the call that is the sink, but instead the element in the command list that corresponds to the file to extract.
Contributor
Author
There was a problem hiding this comment. Done in 5084883 — the sink is now |
||
| } | ||
|
|
||
| /** | ||
| * Holds if `g` clears taint for `tarInfo`. | ||
| * | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Remove (should not be a source).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Done in 5084883 —
ShutilUnpackArchiveSourceremoved.