mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
Marius CiepluchandClaude Opus 5
e127e430ed
Only 11 of the 50 injection pairs contain a framework source token at all. The
other 39 receive untrusted input as a FUNCTION PARAMETER, because SVEN-style
pairs are function-level extractions:
def add_user(username, password):
os.system("useradd ... -p " + encPass + " " + username)
A framework-anchored source model finds nothing there, which caps entailment on
this slice near 22% by construction -- a property of the source model, not of
the engine. More to the point, the flat-IR baseline this feature is measured
against already counted these (source_kinds: ["parameter"]), so a run without
them is not comparable to the 2.2% it is supposed to beat.
The flag is opt-in and off by default, because the two settings are right in
different places: in a function-level pair the function boundary IS the trust
boundary, while across a whole repository most parameters carry internal
values and treating them all as untrusted is not sound. The corpus harness
opts in; a repository scan does not.
On the pair that exposed this the model now resolves both flows, including one
through an intermediate binding:
username -> os.system(...) 2 steps
password -> crypt.crypt(...) -> encPass -> ... 7 steps
Co-Authored-By: Claude Opus 5 (1M context) <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
207 lines
8.9 KiB
Python
207 lines
8.9 KiB
Python
"""model-grounded-detection task 2.2: the taint verdict, and what separates entailed from corroborated.
|
|
|
|
An `ENTAILED` verdict is the static analogue of a reproduced crash: the CPG establishes the flow on its own and
|
|
the LLM's assertion is no longer load-bearing. `CORROBORATED` means a path exists but a sanitizer may break it,
|
|
so the judgement of sufficiency is the LLM's residual — checked against the graph, never averaged over runs.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
|
|
def _cpg(rows: list[dict[str, object]]): # type: ignore[no-untyped-def]
|
|
from openultrasast.cpg.backend import CpgResult
|
|
|
|
return CpgResult(cpg_path=Path("cpg.bin"), run=lambda query, params: rows)
|
|
|
|
|
|
def _spec(): # type: ignore[no-untyped-def]
|
|
from openultrasast.model.specs import TaintSpec
|
|
|
|
return TaintSpec(
|
|
family="injection",
|
|
language="python",
|
|
sources=("request.args",),
|
|
sinks=("os.system", "execute"),
|
|
sanitizers=("escape", "quote"),
|
|
)
|
|
|
|
|
|
def test_an_unsanitized_source_to_sink_path_is_entailed() -> None:
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [
|
|
{"sink": "os.system(cmd)", "sinkLine": "4", "sinkMethod": "run", "source": "request.args['x']", "sanitized": False, "length": 3}
|
|
]
|
|
answer = verdict(_cpg(rows), _spec(), function="run")
|
|
assert answer is not None and answer.rung is Rung.ENTAILED
|
|
assert answer.family == "injection"
|
|
assert "request.args" in answer.witness and "os.system" in answer.witness, "the witness names the flow it found"
|
|
|
|
|
|
def test_a_path_through_a_sanitizer_is_corroborated_not_entailed() -> None:
|
|
"""The model saw the flow but cannot judge whether the sanitizer is sufficient. That residual is the LLM's."""
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [{"sink": "execute(q)", "sinkLine": "9", "sinkMethod": "run", "source": "request.args['q']", "sanitized": True, "length": 4}]
|
|
answer = verdict(_cpg(rows), _spec(), function="run")
|
|
assert answer is not None and answer.rung is Rung.CORROBORATED
|
|
|
|
|
|
def test_no_path_yields_no_verdict_so_the_caller_reports_suspicion() -> None:
|
|
from openultrasast.model.taint import verdict
|
|
|
|
assert verdict(_cpg([]), _spec(), function="run") is None
|
|
|
|
|
|
def test_a_query_that_failed_is_not_read_as_an_absence_of_flow() -> None:
|
|
"""`None` from the engine means "could not decide", which is not the same as "no path" — Req 4.3."""
|
|
from openultrasast.cpg.backend import CpgResult
|
|
from openultrasast.model.taint import verdict
|
|
|
|
broken = CpgResult(cpg_path=Path("cpg.bin"), run=lambda query, params: None)
|
|
assert verdict(broken, _spec(), function="run") is None
|
|
|
|
|
|
def test_the_verdict_is_restricted_to_the_labeled_function() -> None:
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [
|
|
{
|
|
"sink": "os.system(x)", "sinkLine": "40", "sinkMethod": "elsewhere",
|
|
"source": "request.args['x']", "sanitized": False, "length": 2,
|
|
}
|
|
]
|
|
assert verdict(_cpg(rows), _spec(), function="run") is None, "a flow in another function does not judge this one"
|
|
|
|
|
|
def test_the_shortest_unsanitized_flow_wins_and_the_sequence_is_deterministic() -> None:
|
|
"""Req 6.4: two runs over one CPG give an identical verdict sequence, so there is nothing to average."""
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [
|
|
{"sink": "os.system(a)", "sinkLine": "7", "sinkMethod": "run", "source": "request.args['b']", "sanitized": True, "length": 9},
|
|
{"sink": "os.system(a)", "sinkLine": "7", "sinkMethod": "run", "source": "request.args['a']", "sanitized": False, "length": 2},
|
|
]
|
|
first = verdict(_cpg(rows), _spec(), function="run")
|
|
second = verdict(_cpg(rows), _spec(), function="run")
|
|
assert first == second
|
|
assert first is not None and first.rung is Rung.ENTAILED and "request.args['a']" in first.witness
|
|
|
|
|
|
def test_the_spec_drives_the_query_parameters() -> None:
|
|
"""The security modelling is ours; the traversal is the engine's. The spec is what crosses the seam."""
|
|
from openultrasast.cpg.backend import CpgResult
|
|
from openultrasast.model.taint import verdict
|
|
|
|
seen: dict[str, object] = {}
|
|
|
|
def run(query: str, params: dict[str, object]) -> object:
|
|
seen["query"] = query
|
|
seen.update(params)
|
|
return []
|
|
|
|
verdict(CpgResult(cpg_path=Path("cpg.bin"), run=run), _spec(), function="run")
|
|
assert seen["query"] == "taint"
|
|
assert seen["sources"] == ("request.args",)
|
|
assert seen["sinks"] == ("os.system", "execute")
|
|
assert seen["sanitizers"] == ("escape", "quote")
|
|
assert seen["function"] == "run"
|
|
|
|
|
|
# --- the safe-shape test (task 2.3 finding) ------------------------------------------------------------
|
|
#
|
|
# Taint reachability alone does not distinguish a parameterised fix from an interpolated bug: the flow
|
|
# `request.args["name"] -> name -> execute` exists on BOTH sides of the canonical SQL pair.
|
|
#
|
|
# vuln db.execute("select ... '" + name + "'") one argument, interpolated
|
|
# fixed db.execute("select ... = %s", (name,)) two arguments, bound
|
|
#
|
|
# What separates them is the SHAPE of the sink call, which is exactly what `TaintSpec.safe_shape_sinks`
|
|
# preserves. Without this test the model entails both sides and arbitrates nothing.
|
|
|
|
|
|
def _shape_spec(): # type: ignore[no-untyped-def]
|
|
from openultrasast.model.specs import TaintSpec
|
|
|
|
return TaintSpec(
|
|
family="injection",
|
|
language="python",
|
|
sources=("request.args",),
|
|
sinks=("execute",),
|
|
sanitizers=(),
|
|
safe_shape_sinks=("execute",),
|
|
)
|
|
|
|
|
|
def test_a_parameterised_sink_call_is_not_a_vulnerability_even_though_the_flow_reaches_it() -> None:
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [{
|
|
"sink": 'db.execute("select ... = %s", (name,))', "sinkLine": "5", "sinkMethod": "run",
|
|
"source": "request.args['name']", "sanitized": False, "length": 4, "sinkArity": 2, "sinkArg0Literal": True,
|
|
}]
|
|
assert verdict(_cpg(rows), _shape_spec(), function="run") is None, "a bound query is the fix, not the bug"
|
|
|
|
|
|
def test_an_interpolated_sink_call_of_the_same_name_is_entailed() -> None:
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [{
|
|
"sink": 'db.execute("select ... \'" + name + "\'")', "sinkLine": "5", "sinkMethod": "run",
|
|
"source": "request.args['name']", "sanitized": False, "length": 4, "sinkArity": 1, "sinkArg0Literal": False,
|
|
}]
|
|
answer = verdict(_cpg(rows), _shape_spec(), function="run")
|
|
assert answer is not None and answer.rung is Rung.ENTAILED
|
|
|
|
|
|
def test_the_shape_test_only_applies_to_sinks_declared_safe_in_that_shape() -> None:
|
|
"""`os.system(x)` with one argument is not "safe because it has one argument" -- the rule is per sink."""
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [{
|
|
"sink": "os.system(full)", "sinkLine": "7", "sinkMethod": "run",
|
|
"source": "request.args['cmd']", "sanitized": False, "length": 5, "sinkArity": 1, "sinkArg0Literal": False,
|
|
}]
|
|
answer = verdict(_cpg(rows), _spec(), function="run") # os.system is not in safe_shape_sinks
|
|
assert answer is not None and answer.rung is Rung.ENTAILED
|
|
|
|
|
|
def test_a_row_without_shape_fields_is_judged_on_the_flow_alone() -> None:
|
|
"""Older rows, or an engine that could not report arity, must not be silently treated as safe."""
|
|
from openultrasast.model.ladder import Rung
|
|
from openultrasast.model.taint import verdict
|
|
|
|
rows = [{"sink": "db.execute(q)", "sinkLine": "5", "sinkMethod": "run", "source": "request.args['n']",
|
|
"sanitized": False, "length": 3}]
|
|
answer = verdict(_cpg(rows), _shape_spec(), function="run")
|
|
assert answer is not None and answer.rung is Rung.ENTAILED
|
|
|
|
|
|
def test_parameter_sources_are_opt_in_and_reach_the_query() -> None:
|
|
"""A function-level pair's parameters are its trust boundary; a whole repository's are not.
|
|
|
|
39 of the 50 injection pairs carry no framework source token at all — their untrusted input arrives as a
|
|
function parameter — and the flat-IR baseline this feature is measured against counted those as sources.
|
|
So the flag must exist and must default to off.
|
|
"""
|
|
from openultrasast.cpg.backend import CpgResult
|
|
from openultrasast.model.taint import verdict
|
|
|
|
seen: dict[str, object] = {}
|
|
|
|
def run(query: str, params: dict[str, object]) -> object:
|
|
seen.update(params)
|
|
return []
|
|
|
|
verdict(CpgResult(cpg_path=Path("c.bin"), run=run), _spec(), function="run")
|
|
assert seen["parameterSources"] == "false", "treating every parameter as untrusted is not the default"
|
|
verdict(CpgResult(cpg_path=Path("c.bin"), run=run), _spec(), function="run", parameter_sources=True)
|
|
assert seen["parameterSources"] == "true"
|