coretrace-python-analyzer 0.13.0__py3-none-any.whl → 0.14.0__py3-none-any.whl

coretrace_python/__init__.py

@@ -1,4 +1,4 @@
 """CoreTrace's Python static analysis frontend."""
 
-__version__ = "0.13.0"
+__version__ = "0.14.0"
 

coretrace_python/abstract/strings.py

@@ -0,0 +1,98 @@
+"""The constant text a string starts with (architecture §18): what ``+`` and f-strings
+build from string literals and from module-level names bound once to one. Anything
+else, a parameter, a call result, an import, ``%`` or ``format``, is text of unknown
+value."""
+
+from __future__ import annotations
+
+from collections.abc import Mapping
+from types import MappingProxyType
+from typing import ClassVar
+
+from coretrace_python.analysis import Analysis, AnalysisContext, AnyAnalysis
+from coretrace_python.cfg import CFGError
+from coretrace_python.hir import nodes
+from coretrace_python.ir.lowering import (
+    MODULE_BODY,
+    LoweringError,
+    PyIRAnalysis,
+    analyzable_functions,
+)
+from coretrace_python.ir.model import (
+    BinaryOp,
+    BuildString,
+    Constant,
+    ForNext,
+    Global,
+    Instruction,
+    SetGlobal,
+    StoreLocal,
+    Value,
+)
+
+
+def leading_text(value: Value, defs: Mapping[Value, Instruction], strings: Mapping[str, str]) -> tuple[str, bool]:
+    """The constant text ``value`` starts with, and whether that text is all of it, given
+    the definitions of the function's values and the module's ``strings``."""
+
+    made = defs.get(value)
+    if isinstance(made, Constant):
+        return (made.value, True) if isinstance(made.value, str) else ("", False)
+    if isinstance(made, Global):
+        known = strings.get(made.name)
+        return ("", False) if known is None else (known, True)
+    if isinstance(made, BinaryOp) and made.operator == "add":
+        left, whole = leading_text(made.left, defs, strings)
+        if not whole:
+            return left, False
+        right, whole = leading_text(made.right, defs, strings)
+        return left + right, whole
+    if isinstance(made, BuildString):
+        text = ""
+        for part in made.parts:
+            piece, whole = leading_text(part, defs, strings)
+            text += piece
+            if not whole:
+                return text, False
+        return text, True
+    return "", False
+
+
+class ModuleStringsAnalysis(Analysis[Mapping[str, str]]):
+    """The module-level names bound once, to a string literal, and never rebound: by no
+    other statement of the module body, no function assigning them as ``global``, no
+    definition of that name. A module that does not lower entirely has none."""
+
+    name: ClassVar[str] = "abstract.module_strings"
+    requires: ClassVar[frozenset[AnyAnalysis]] = frozenset({PyIRAnalysis})
+
+    @classmethod
+    def compute(cls, ctx: AnalysisContext) -> Mapping[str, str]:
+        try:
+            functions = [ctx.get(PyIRAnalysis, function) for function in analyzable_functions(ctx.module)]
+        except (LoweringError, CFGError):
+            return MappingProxyType({})
+        body = next((function for function in functions if function.name == MODULE_BODY), None)
+        if body is None:
+            return MappingProxyType({})
+        defs = {i.result: i for block in body.blocks for i in block.instructions if i.result is not None}
+        stored: dict[str, list[Value | None]] = {}
+        for block in body.blocks:
+            for instruction in block.instructions:
+                if isinstance(instruction, StoreLocal):
+                    stored.setdefault(instruction.name, []).append(instruction.value)
+            if isinstance(block.terminator, ForNext):
+                # A ``for`` binds its target to each item.
+                stored.setdefault(block.terminator.target, []).append(None)
+        rebound = {
+            i.name for function in functions for block in function.blocks for i in block.instructions
+            if isinstance(i, SetGlobal)
+        }
+        rebound |= {s.name for s in ctx.module.body if isinstance(s, nodes.Function | nodes.Class)}
+        found: dict[str, str] = {}
+        for name, values in stored.items():
+            value = values[0] if len(values) == 1 and name not in rebound else None
+            made = defs.get(value) if value is not None else None
+            if isinstance(made, Constant) and isinstance(made.value, str):
+                found[name] = made.value
+        return MappingProxyType(found)

coretrace_python/bundled/security/ssrf/plugin.toml

@@ -1,7 +1,7 @@
 name = "ssrf"
 version = "1.0.0"
 plugin_api = ">=1,<2"
-requires = ["taint.flows", "findings.refutation"]
+requires = ["taint.flows", "findings.refutation", "ir.ssa", "abstract.module_strings"]
 provides = ["vulnerability.ssrf"]
 
 [entrypoint]

coretrace_python/bundled/security/ssrf/ssrf.py

@@ -1,12 +1,37 @@
-"""Server-side request forgery: attacker-controlled input reaching a SSRF sink."""
+"""Server-side request forgery: attacker-controlled input reaching a SSRF sink.
+
+How the URL is built, with ``+`` and f-strings, can prove part of its destination. Constant
+text fixing ``scheme://host`` and ending the authority with ``/``, ``?`` or ``#`` before
+any input keeps the input from choosing the host; the input still chooses the path, which
+may reach a sensitive resource of that host, and a redirect may lead elsewhere, so the
+flow is a hotspot. With the path fixed too, the input reaching the query or fragment
+only, and redirects disabled in the call, the destination is fixed and the flow is
+refuted. Anything unproven, a base of unknown value or a URL built in a helper function,
+stays a vulnerability.
+"""
 
 from __future__ import annotations
 
+import re
 from typing import ClassVar
 
+from coretrace_python.abstract.strings import ModuleStringsAnalysis, leading_text
+from coretrace_python.analysis import AnyAnalysis
 from coretrace_python.findings import Severity
-from coretrace_python.plugins import TaintDetector
-from coretrace_python.taint import TaintKind
+from coretrace_python.findings.refutation import Status, Verdict
+from coretrace_python.hir import nodes
+from coretrace_python.ir.ssa import SSAAnalysis
+from coretrace_python.plugins import PluginContext, TaintDetector
+from coretrace_python.taint import TaintFlow, TaintKind
+
+# ``scheme://`` and an authority ended by ``/``, ``?`` or ``#``. A backslash, which some
+# URL parsers take for a slash, does not end it here.
+_FIXED_HOST = re.compile(r"[A-Za-z][A-Za-z0-9+.-]*://[^/?#\\]+[/?#]")
+# The same with the path fixed too: what follows is query or fragment.
+_FIXED_PATH = re.compile(r"[A-Za-z][A-Za-z0-9+.-]*://[^/?#\\]+(?:/[^?#]*)?[?#]")
+# A client honours the one of these keywords it knows and rejects the other with a
+# ``TypeError``: either way, the call follows no redirect.
+_NO_REDIRECTS = ("allow_redirects", "follow_redirects")
 
 
 class SsrfPlugin(TaintDetector):
@@ -15,3 +40,25 @@ class SsrfPlugin(TaintDetector):
     kind: ClassVar[TaintKind] = TaintKind.SSRF
     severity: ClassVar[Severity] = Severity.HIGH
     title: ClassVar[str] = "Server-side request forgery"
+    requires: ClassVar[frozenset[AnyAnalysis]] = TaintDetector.requires | {SSAAnalysis, ModuleStringsAnalysis}
+
+    def judge(self, ctx: PluginContext, function: nodes.Function, flow: TaintFlow, verdict: Verdict) -> Verdict:
+        if flow.through is not None:
+            return verdict  # the URL is built in the callee
+        ssa = ctx.get(SSAAnalysis, function)
+        defs = {i.result: i for block in ssa.blocks for i in block.instructions if i.result is not None}
+        text, _ = leading_text(flow.argument, defs, ctx.get(ModuleStringsAnalysis))
+        host = _FIXED_HOST.match(text)
+        if host is None:
+            return verdict
+        arguments = flow.sink_arguments
+        no_redirects = arguments is not None and any(arguments.given(name) == (True, "False") for name in _NO_REDIRECTS)
+        if _FIXED_PATH.match(text) is not None:
+            if no_redirects:
+                return Verdict(flow, Status.REFUTED, f"the destination is fixed by {text!r} and redirects are disabled")
+            left = "a redirect may lead elsewhere"
+        else:
+            left = "the input chooses the path" + ("" if no_redirects else ", and a redirect may lead elsewhere")
+        if verdict.status is not Status.VULNERABILITY:
+            return verdict
+        return Verdict(flow, Status.HOTSPOT, f"the host is fixed by {host.group(0)!r}, but {left}")

coretrace_python/engine.py

@@ -17,6 +17,7 @@ from typing import Any, ClassVar
 
 from coretrace_python import __version__
 from coretrace_python.abstract import ConstantPropagation, HeapAnalysis, RangeAnalysis
+from coretrace_python.abstract.strings import ModuleStringsAnalysis
 from coretrace_python.analysis import (
     AnalysisContext,
     AnalysisManager,
@@ -143,6 +144,7 @@ ALL_ANALYSES: tuple[AnyAnalysis, ...] = (
     DefUseAnalysis,
     ConstantPropagation,
     RangeAnalysis,
+    ModuleStringsAnalysis,
     HeapAnalysis,
     CallGraphAnalysis,
     SummaryAnalysis,

coretrace_python/plugins/detectors.py

@@ -13,13 +13,14 @@ from typing import ClassVar
 
 from coretrace_python.analysis import AnyAnalysis
 from coretrace_python.findings import Confidence, Finding, Severity
-from coretrace_python.findings.refutation import RefutationAnalysis, Status
+from coretrace_python.findings.refutation import RefutationAnalysis, Status, Verdict
+from coretrace_python.hir import nodes
 from coretrace_python.interprocedural import CallGraphAnalysis
 from coretrace_python.ir.model import Call, Instruction, Symbol, Value
 from coretrace_python.ir.ssa import SSAAnalysis
 from coretrace_python.plugins.api import Plugin, PluginContext
 from coretrace_python.semantic.symbols import SymbolId
-from coretrace_python.taint import TaintAnalysis, TaintKind
+from coretrace_python.taint import TaintAnalysis, TaintFlow, TaintKind
 
 
 class TaintDetector(Plugin):
@@ -40,6 +41,9 @@ class TaintDetector(Plugin):
                 if not flow.kinds & self.kind:
                     continue
                 verdict = verdicts.verdict(flow)
+                if verdict.status is Status.REFUTED:
+                    continue
+                verdict = self.judge(ctx, function, flow, verdict)
                 if verdict.status is Status.REFUTED:
                     continue
                 message = f"{self.title}: {flow.source.label} input reaches {flow.sink.symbol}"
@@ -70,6 +74,13 @@ class TaintDetector(Plugin):
                 )
         return findings
 
+    def judge(self, ctx: PluginContext, function: nodes.Function, flow: TaintFlow, verdict: Verdict) -> Verdict:
+        """This rule's verdict on ``flow``, given the refutation's: the same, unless the rule
+        knows more about its own sinks. The refutation's verdict, which other consumers
+        of the flow read, does not change."""
+
+        return verdict
+
 
 def _lower(confidence: Confidence) -> Confidence:
     return {Confidence.HIGH: Confidence.MEDIUM}.get(confidence, Confidence.LOW)

{coretrace_python_analyzer-0.13.0.dist-info → coretrace_python_analyzer-0.14.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: coretrace-python-analyzer
-Version: 0.13.0
+Version: 0.14.0
 Summary: Static security analysis infrastructure for Python code
 Project-URL: Homepage, https://github.com/CoreTrace/coretrace-python-analyzer
 Project-URL: Repository, https://github.com/CoreTrace/coretrace-python-analyzer

{coretrace_python_analyzer-0.13.0.dist-info → coretrace_python_analyzer-0.14.0.dist-info}/RECORD

@@ -1,12 +1,13 @@
-coretrace_python/__init__.py,sha256=4_uvCC4RHPELcdUoMgQ00MwplbVOBvuK0TpVzxBnXII,76
+coretrace_python/__init__.py,sha256=kY0Q5RzkkixmFjJXYSXgYgHOkh327TcAyqMH9u0a_M0,76
 coretrace_python/__main__.py,sha256=V8DnYtRboISK2VCKm7DGHLREKvqLbqApyWlKBOs26wU,65
 coretrace_python/cache.py,sha256=-pZv-ELm4jMCTXQWSZIobHaT9UHIjFu7IlMkOM0i4LI,13607
 coretrace_python/cli.py,sha256=G5jhb6g6RgSRSjjS7DBgziIjUM1vTFwalJGvFHVKxrg,11225
-coretrace_python/engine.py,sha256=nwK8fbcEOT0zKiBlK67aCl7yiQpE00j56LLknXn7Djg,32276
+coretrace_python/engine.py,sha256=yICn93LZyoWOdDoZEIqoWATuhPQhLPW8ANLxJPskDwM,32371
 coretrace_python/abstract/__init__.py,sha256=n5FNkV8Z4LmwG0r06KWdLj4N2CPSgAKwY3896tdmRgM,999
 coretrace_python/abstract/constants.py,sha256=z4-e7IzysxzGi58wFFff1MlEoV8l7AZsB9EL-q6b7vY,9071
 coretrace_python/abstract/heap.py,sha256=OaESXFGC0qzyhAr76xrCu4skeDVzZM4wlenQqfMTkdk,9642
 coretrace_python/abstract/ranges.py,sha256=zEl9ee55u3E02tkYzzIvCCud5mYRKIUgZd9h_0-crCM,11547
+coretrace_python/abstract/strings.py,sha256=G5EGlhxjrpjU9TuXQifuVO-6MNMrUtZ_4S3nkMEvIuQ,4095
 coretrace_python/abstract/values.py,sha256=SQmgR8jo7cd8KJFDokejg-cFTjJU1CTBUPYyEvbMg-4,1739
 coretrace_python/analysis/__init__.py,sha256=hE7lDwXOdA05_aSZaERRgMv0C2ev8jjJbz4xvrja4Og,728
 coretrace_python/analysis/manager.py,sha256=suoIrPwimyu1AjF6BJwpqAkJBwe6XxzQu9JwV2TN2aQ,5843
@@ -63,8 +64,8 @@ coretrace_python/bundled/security/plaintext_credentials/plaintext_credentials.py
 coretrace_python/bundled/security/plaintext_credentials/plugin.toml,sha256=W56wUdAdf7NNirfQhTdKrn-cCwebqmvkRJg9OVFJUyM,263
 coretrace_python/bundled/security/sql_injection/plugin.toml,sha256=U35h6YdbbM93Ar_msWrwY98_bb6rN-qaa1e7XOtPeSo,224
 coretrace_python/bundled/security/sql_injection/sql_injection.py,sha256=W-ppZngb9mLwRjJPGkh__8kaDqYdSrVbciv0mPdYFNE,545
-coretrace_python/bundled/security/ssrf/plugin.toml,sha256=OySYgL9rGh1f4UuVpEOWdgcyp0vAmaP1m2IJ8Al6Ddc,189
-coretrace_python/bundled/security/ssrf/ssrf.py,sha256=bshcPZMjuQtTR4203CUTxFGZuwIYfsi58rnE5XdqKXc,549
+coretrace_python/bundled/security/ssrf/plugin.toml,sha256=Uh0hvcc2bkOEKBQUw6tyuvpPQRq8_JzhWc9nVQAdm1Y,226
+coretrace_python/bundled/security/ssrf/ssrf.py,sha256=Zk3eCu4Gp9vnR4DarG_RAm9U7hNv2ESAn_oVUVUMHF8,3441
 coretrace_python/bundled/security/xss/plugin.toml,sha256=o6aZWoDNCG6CJ11JDa5lVR0v6NHh-Jg5QpNRxoGSJaw,185
 coretrace_python/bundled/security/xss/xss.py,sha256=hzhoblPMivtwoWZ4v7YyAb15GGisX_imGWgxFzCDeqA,532
 coretrace_python/bundled/syntax/dangerous_eval/dangerous_eval.py,sha256=_ktrigLDf-XTKjWtYX-_wZ9-Gb3G4bCzRhpU0Xj-c1g,723
@@ -124,7 +125,7 @@ coretrace_python/ir/printer.py,sha256=otBIhZUvB_UfB68gid_FbPcSjBUSmxH3v7vBMZZQVk
 coretrace_python/ir/ssa.py,sha256=cIYbcv90PI6AOeMrw2ZWp88fy7E2ZO4P3tqjtPHra7g,11116
 coretrace_python/plugins/__init__.py,sha256=xRKqkvkvQMmfQACHHoBioYhIyyK4HoMAVogy6EZG8tg,1398
 coretrace_python/plugins/api.py,sha256=FcIe2c4sFB-PAPtYcJkidvdZJkr_xFKT8SvlBP5l38o,8603
-coretrace_python/plugins/detectors.py,sha256=ej5Z_MS0CBqrR4b9xycjTVUIo5arpArpdbr7nL732iI,5700
+coretrace_python/plugins/detectors.py,sha256=9c6yaLvf5nwtiiIskLd9WE_R4IE_RcqjOD5c-SH0SuI,6274
 coretrace_python/plugins/loader.py,sha256=Use-lHTL4-IJYQBZmODC89zhJbYKGvDSLZHWjZa5NaI,3885
 coretrace_python/plugins/manifest.py,sha256=F24pgQSwApRUL6ZihRSLv9wL_M03A_pZjrj9Zi4Ku3Q,3438
 coretrace_python/plugins/registry.py,sha256=ixKcT2YDky96TWCFckdzKnGRmFn1dbBVMSZLPvdxvY8,1177
@@ -147,9 +148,9 @@ coretrace_python/taint/engine.py,sha256=rEAbwjR5v294PqBzBlu6f9WiMvVmwV83FqdsWbT4
 coretrace_python/taint/models.py,sha256=8AwPKKdmwAHmE7CxwUbtWn5w7JVkEJ06_Is7xQWTx38,17066
 coretrace_python/taint/routes.py,sha256=UAJKXcw_sM9shf58FfDroxVO9bNSm4qrQdZknwUB0lo,6110
 coretrace_python/taint/templates.py,sha256=8Ojb43VXuWxOVifeXRpi3_2mjZfnvIC7GQ-AW80GUYk,11148
-coretrace_python_analyzer-0.13.0.dist-info/METADATA,sha256=XNQT5nbo6DGzDqYJw9p1sYyciIkdituTpM82-o3z8-8,3217
-coretrace_python_analyzer-0.13.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
-coretrace_python_analyzer-0.13.0.dist-info/entry_points.txt,sha256=wdozemiraOkbt65g_Y_zgspuZpoLxJdaCVMJt1Ft3c0,72
-coretrace_python_analyzer-0.13.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-coretrace_python_analyzer-0.13.0.dist-info/licenses/NOTICE,sha256=s3VHj5ngV0ozjW_kZJpg_35ne6JwoBK0ysOjbqVtA0w,113
-coretrace_python_analyzer-0.13.0.dist-info/RECORD,,
+coretrace_python_analyzer-0.14.0.dist-info/METADATA,sha256=I6joOK1gGJSOzcn3pJ9PYii-2Yb7Ak-PSK9SmQWz4vQ,3217
+coretrace_python_analyzer-0.14.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+coretrace_python_analyzer-0.14.0.dist-info/entry_points.txt,sha256=wdozemiraOkbt65g_Y_zgspuZpoLxJdaCVMJt1Ft3c0,72
+coretrace_python_analyzer-0.14.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+coretrace_python_analyzer-0.14.0.dist-info/licenses/NOTICE,sha256=s3VHj5ngV0ozjW_kZJpg_35ne6JwoBK0ysOjbqVtA0w,113
+coretrace_python_analyzer-0.14.0.dist-info/RECORD,,