8000 Fix String.replace instrumentation for IAST by Mariovido · Pull Request #8281 · DataDog/dd-trace-java · GitHub
[go: up one dir, main page]
Skip to content

Fix String.replace instrumentation for IAST #8281

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
merged 5 commits into from
Jan 30, 2025
Merged

Fix String.replace instrumentation for IAST #8281

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6dc12f5
Fix algorithm of replace(CharSequence, CharSequence) + adding new tests
Mariovido Jan 24, 2025
2502bd6
Fix tests
Mariovido Jan 24, 2025
a6353bc
Optimize quoteReplacement to be executed only once
Mariovido Jan 24, 2025
1c08728
Return replacedString if everything is fine
Mariovido Jan 28, 2025
d23ea24
Merge branch 'master' into mario.vidal/fix_replace
Mariovido Jan 30, 2025
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: 2 additions & 2 deletions dd-java-agent/agent-iast/src/main/java/com/datadog/iast/propagation/StringModuleImpl.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -749,8 +749,8 @@ public String onStringReplace(
return StringUtils.replaceAndTaint(
taintedObjects,
self,
Pattern.compile((String) oldCharSeq),
(String) newCharSeq,
Pattern.compile(oldCharSeq.toString(), Pattern.LITERAL),
newCharSeq.toString(),
rangesSelf,
rangesInput,
Integer.MAX_VALUE);
Expand Down
7 changes: 6 additions & 1 deletion dd-java-agent/agent-iast/src/main/java/com/datadog/iast/util/StringUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,11 @@ public static String replaceAndTaint(
int firstRange = 0;
int newLength = replacement.length();

// In case there is a '\' or '$' in the replacement string we need to make a
// quoteReplacement
// If there is no '\' or '$' it will return the same string.
String finalReplacement = Matcher.quoteReplacement(replacement);

boolean canAddRange = true;
StringBuffer sb = new StringBuffer();
do {
Expand Down Expand Up @@ -165,7 +170,7 @@ public static String replaceAndTaint(
canAddRange = newRanges.add(rangesInput, start + offset);
}

matcher.appendReplacement(sb, replacement);
matcher.appendReplacement(sb, finalReplacement);

offset = diffLength;
numOfReplacements--;
Expand Down
102 changes: 68 additions & 34 deletions ...ava-agent/agent-iast/src/test/groovy/com/datadog/iast/propagation/StringModuleTest.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1252,13 +1252,15 @@ class StringModuleTest extends IastModuleImplTestBase {
given:
final taintedObjects = ctx.getTaintedObjects()
def self = addFromTaintFormat(taintedObjects, testString)
def originalReplace = self.replace(oldCharSeq, newCharSeq)

when:
def result = module.onStringReplace(self, oldCharSeq, newCharSeq)
def taintedObject = taintedObjects.get(result)

then:
1 * tracer.activeSpan() >> span
originalReplace == result
taintFormat(result, taintedObject.getRanges()) == expected

where:
Expand All @@ -1277,52 +1279,69 @@ class StringModuleTest extends IastModuleImplTestBase {
"==>my_o<==u==>tput<==" | 'out' | 'in' | "==>my_<==in==>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | 'in' | "==>my_<==in==>put<====>my_<==in==>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | 'input' | "==>my_<==input"
"==>my_input<==" | '_' | '/\\,.*+' | "==>my<==/\\,.*+==>input<=="
"==>my_input<==" | '_' | '!?^&$#' | "==>my<==!?^&\$#==>input<=="
"==>my_input<==" | '_' | ')(][}{' | "==>my<==)(][}{==>input<=="
}

void 'test replace with a char sequence (tainted) and make sure IastRequestContext is called'() {
given:
final taintedObjects = ctx.getTaintedObjects()
def self = addFromTaintFormat(taintedObjects, testString)
def inputTainted = addFromTaintFormat(taintedObjects, newCharSeq)
def originalReplace = self.replace(oldCharSeq, inputTainted)

when:
def result = module.onStringReplace(self, oldCharSeq, inputTainted)
def taintedObject = taintedObjects.get(result)

then:
1 * tracer.activeSpan() >> span
originalReplace == result
taintFormat(result, taintedObject.getRanges()) == expected

where:
testString | oldCharSeq | newCharSeq | expected
"==>masquita<==" | 'as' | '==>os<==' | "==>m<====>os<====>quita<=="
"==>masquita<==" | 'os' | '==>as<==' | "==>masquita<=="
"masquita" | 'as' | '==>os<==' | "m==>os<==quita"
"==>m<==as==>qu<==i==>ta<==" | 'as' | '==>os<==' | "==>m<====>os<====>qu<==i==>ta<=="
"==>my_input<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_output<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<=="
"==>my_input<==" | '_' | '==>-<==' | "==>my<====>-<====>input<=="
"==>my<==_==>input<==" | 'in' | '==>out<==' | "==>my<==_==>out<====>put<=="
"==>my_in<==p==>ut<==" | 'in' | '==>out<==' | "==>my_<====>out<==p==>ut<=="
"==>my_<==in==>put<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_i<==n==>put<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_<==i==>nput<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_o<==u==>tput<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<====>my_<====>in<====>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | '==>input<==' | "==>my_<====>input<=="
testString | oldCharSeq | newCharSeq | expected
"==>masquita<==" | 'as' | '==>os<==' | "==>m<====>os<====>quita<=="
"==>masquita<==" | 'os' | '==>as<==' | "==>masquita<=="
"masquita" | 'as' | '==>os<==' | "m==>os<==quita"
"==>m<==as==>qu<==i==>ta<==" | 'as' | '==>os<==' | "==>m<====>os<====>qu<==i==>ta<=="
"==>my_input<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_output<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<=="
"==>my_input<==" | '_' | '==>-<==' | "==>my<====>-<====>input<=="
"==>my<==_==>input<==" | 'in' | '==>out<==' | "==>my<==_==>out<====>put<=="
"==>my_in<==p==>ut<==" | 'in' | '==>out<==& 10000 #39; | "==>my_<====>out<==p==>ut<=="
"==>my_<==in==>put<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_i<==n==>put<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_<==i==>nput<==" | 'in' | '==>out<==' | "==>my_<====>out<====>put<=="
"==>my_o<==u==>tput<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | "==>my_<====>in<====>put<====>my_<====>in<====>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | '==>input<==' | "==>my_<====>input<=="
"==>my_input<==" | '_' | '==>/\\,.*+<==' | "==>my<====>/\\,.*+<====>input<=="
"==>my_input<==" | '_' | '==>!?^&$#<==' | "==>my<====>!?^&\$#<====>input<=="
"==>my_input<==" | '_' | '==>)(][}{<==' | "==>my<====>)(][}{<====>input<=="
}

void 'test replace with a regex and replacement (not tainted) and make sure IastRequestContext is called'() {
given:
final taintedObjects = ctx.getTaintedObjects()
def self = addFromTaintFormat(taintedObjects, testString)
def originalReplace
if (numReplacements > 1) {
originalReplace = self.replaceAll(regex, replacement)
} else {
originalReplace = self.replaceFirst(regex, replacement)
}

when:
def result = module.onStringReplace(self, regex, replacement, numReplacements)
def taintedObject = taintedObjects.get(result)

then:
1 * tracer.activeSpan() >> span
if (numReplacements > 0) {
originalReplace == result
}
taintFormat(result, taintedObject.getRanges()) == expected

where:
Expand All @@ -1341,41 +1360,56 @@ class StringModuleTest extends IastModuleImplTestBase {
"==>my_o<==u==>tput<==" | 'out' | 'in' | Integer.MAX_VALUE | "==>my_<==in==>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | 'in' | Integer.MAX_VALUE | "==>my_<==in==>put<====>my_<==in==>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | 'input' | Integer.MAX_VALUE | "==>my_<==input"
"==>my_input<==" | '_' | '/\\,.*+' | Integer.MAX_VALUE | "==>my<==/\\,.*+==>input<=="
"==>my_input<==" | '_' | '!?^&#' | Integer.MAX_VALUE | "==>my<==!?^&#==>input<=="
"==>my_input<==" | '_' | ')(][}{' | Integer.MAX_VALUE | "==>my<==)(][}{==>input<=="
}

void 'test replace with a regex and replacement (tainted) and make sure IastRequestContext is called'() {
given:
final taintedObjects = ctx.getTaintedObjects()
def self = addFromTaintFormat(taintedObjects, testString)
def inputTainted = addFromTaintFormat(taintedObjects, replacement)
def originalReplace
if (numReplacements > 1) {
originalReplace = self.replaceAll(regex, inputTainted)
} else {
originalReplace = self.replaceFirst(regex, inputTainted)
}

when:
def result = module.onStringReplace(self, regex, inputTainted, numReplacements)
def taintedObject = taintedObjects.get(result)

then:
1 * tracer.activeSpan() >> span
if (numReplacements > 0) {
originalReplace == result
}
taintFormat(result, taintedObject.getRanges()) == expected

where:
testString | regex | replacement | numReplacements | expected
"==>masquita<==" | 'as' | '==>os<==' | Integer.MAX_VALUE | "==>m<====>os<====>quita<=="
"==>masquita<==" | 'os' | '==>as<==' | Integer.MAX_VALUE | "==>masquita<=="
"masquita" | 'as' | '==>os<==' | Integer.MAX_VALUE | "m==>os<==quita"
"==>m<==as==>qu<==i==>ta<==" | 'as' | '==>os<==' | Integer.MAX_VALUE | "==>m<====>os<====>qu<==i==>ta<=="
"==>my_input<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_output<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<=="
"==>my_input<==" | '_' | '==>-<==' | Integer.MAX_VALUE | "==>my<====>-<====>input<=="
"==>my<==_==>input<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my<==_==>out<====>put<=="
"==>my_in<==p==>ut<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<==p==>ut<=="
"==>my_<==in==>put<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_i<==n==>put<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_<==i==>nput<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_o<==u==>tput<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<====>my_<====>in<====>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | '==>input<==' | Integer.MAX_VALUE | "==>my_<====>input<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | 1 | "==>my_<====>in<====>put<====>my_o<==u==>tput<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | 0 | "==>my_o<==u==>tput<====>my_o<==u==>tput<=="
testString | regex | replacement | numReplacements | expected
"==>masquita<==" | 'as' | '==>os<==' | Integer.MAX_VALUE | "==>m<====>os<====>quita<=="
"==>masquita<==" | 'os' | '==>as<==' | Integer.MAX_VALUE | "==>masquita<=="
"masquita" | 'as' | '==>os<==' | Integer.MAX_VALUE | "m==>os<==quita"
"==>m<==as==>qu<==i==>ta<==" | 'as' | '==>os<==' | Integer.MAX_VALUE | "==>m<====>os<====>qu<==i==>ta<=="
"==>my_input<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_output<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<=="
"==>my_input<==" | '_' | '==>-<==' | Integer.MAX_VALUE | "==>my<====>-<====>input<=="
"==>my<==_==>input<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my<==_==>out<====>put<=="
"==>my_in<==p==>ut<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<==p==>ut<=="
"==>my_<==in==>put<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_i<==n==>put<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_<==i==>nput<==" | 'in' | '==>out<==' | Integer.MAX_VALUE | "==>my_<====>out<====>put<=="
"==>my_o<==u==>tput<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | Integer.MAX_VALUE | "==>my_<====>in<====>put<====>my_<====>in<====>put<=="
"==>my_o<==u==>tp<==ut" | 'output' | '==>input<==' | Integer.MAX_VALUE | "==>my_<====>input<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | 1 | "==>my_<====>in<====>put<====>my_o<==u==>tput<=="
"==>my_o<==u==>tput<====>my_o<==u==>tput<==" | 'out' | '==>in<==' | 0 | "==>my_o<==u==>tput<====>my_o<==u==>tput<=="
"==>my_input<==" | '_' | '==>/\\,.*+<==' | Integer.MAX_VALUE | "==>my<====>/\\,.*+<====>input<=="
"==>my_input<==" | '_' | '==>!?^&#<==' | Integer.MAX_VALUE | "==>my<====>!?^&#<====>input<=="
"==>my_input<==" | '_' | '==>)(][}{<==' | Integer.MAX_VALUE | "==>my<====>)(][}{<====>input<=="
}

void 'test valueOf with (#param) and make sure IastRequestContext is called'() {
Expand Down
Loading
0