Skip to content

alexgreensh/repo-forensics / skills/repo-forensics

repo-forensics

Flagged

Security forensics for git repos, AI skills, and MCP servers. Audits dependencies, detects prompt injection, credential theft, runtime dynamism, manifest drift, known CVEs, CISA KEV (actively exploited) vulns, and 2026 attack patterns. Not for fixing vulnerabilities or pentesting.

FileKindSize
.gitignoreother193 B
SKILL.mdskill md43.4 KB
checksums.jsonconfig10.8 KB
checksums.json.sigother64 B
data/README.mdmarkdown1.3 KB
data/compromised_versions.jsonconfig188.3 KB
data/rule_ids.csvother35.3 KB
data/rulepacks/.gitkeepother221 B
data/rulepacks/dead_anchors.jsonconfig9.0 KB
data/rulepacks/mcp_security.jsonconfig31.2 KB
data/rulepacks/runtime_dynamism.jsonconfig46.7 KB
data/rulepacks/sast.jsonconfig107.6 KB
data/rulepacks/secrets.jsonconfig30.4 KB
data/rulepacks/shared.jsonconfig4.4 KB
data/rulepacks/skill_threats.jsonconfig95.4 KB
data/runtime_floors.jsonconfig2.3 KB
data/yara/cryptominers.yarother1.8 KB
data/yara/hacktools.yarother2.2 KB
data/yara/malware.yarother2.2 KB
data/yara/manifest.jsonconfig8.0 KB
data/yara/webshells.yarother2.5 KB
references/cursor-hook-contract.mdmarkdown5.6 KB
references/kernel_privesc_sandbox_pack.mdmarkdown5.0 KB
references/mcp-attack-patterns.mdmarkdown8.7 KB
references/research_sources.mdmarkdown8.0 KB
references/threat_patterns.mdmarkdown20.3 KB
scripts/_context_gate.pyscript21.7 KB
scripts/_ed25519.pyscript5.1 KB
scripts/_pyc_unmarshal.pyscript17.1 KB
scripts/_shared_patterns.pyscript4.8 KB
scripts/adjudication.pyscript16.4 KB
scripts/adjudication_bridge.pyscript1.0 KB
scripts/aggregate_json.pyscript69.2 KB
scripts/auto_scan.pyexecutablescript152.1 KB
scripts/corpus_sync.pyscript10.0 KB
scripts/cursor_pre_scan.pyscript22.5 KB
scripts/dast_sandbox.sbother1.6 KB
scripts/dead_anchors_extract.pyscript14.8 KB
scripts/dead_anchors_probe.pyscript27.1 KB
scripts/forensics_core.pyscript176.5 KB
scripts/gen_rule_ids.pyscript8.6 KB
scripts/hook_adapter.pyscript19.4 KB
scripts/ioc_manager.pyscript49.6 KB
scripts/parse_pnpm_lock.pyscript7.9 KB
scripts/pre_scan.pyscript143.5 KB
scripts/pypi_pins.pyscript8.1 KB
scripts/refresh_controller.pyexecutablescript48.4 KB
scripts/refresh_threat_dbs.pyexecutablescript19.4 KB
scripts/rule_loader.pyscript44.8 KB
scripts/rulepack_feed.pyscript26.4 KB
scripts/run_forensics.shexecutablescript20.3 KB
scripts/sarif_export.pyscript18.6 KB
scripts/scan_agent_skills.pyscript33.2 KB
scripts/scan_archive.pyscript29.1 KB
scripts/scan_ast.pyscript44.9 KB
scripts/scan_binary.pyscript10.9 KB
scripts/scan_bytecode.pyscript28.2 KB
scripts/scan_dast.pyscript28.8 KB
scripts/scan_dataflow.pyscript15.4 KB
scripts/scan_dead_anchors.pyscript15.9 KB
scripts/scan_decode.pyscript37.5 KB
scripts/scan_dependencies.pyscript124.5 KB
scripts/scan_devcontainer.pyscript8.5 KB
scripts/scan_entropy.pyscript15.6 KB
scripts/scan_entrypoint.pyscript34.3 KB
scripts/scan_git_config.pyscript96.3 KB
scripts/scan_git_forensics.pyscript24.1 KB
scripts/scan_history.pyscript14.5 KB
scripts/scan_infra.pyscript54.3 KB
scripts/scan_integrity.pyscript41.0 KB
scripts/scan_lifecycle.pyscript65.1 KB
scripts/scan_manifest_drift.pyscript47.0 KB
scripts/scan_mcp_security.pyscript42.3 KB
scripts/scan_oversize.pyscript11.7 KB
scripts/scan_post_incident.pyscript36.9 KB
scripts/scan_provenance.pyscript19.4 KB
scripts/scan_runtime_dynamism.pyscript23.5 KB
scripts/scan_runtime_floors.pyscript33.5 KB
scripts/scan_sast.pyscript59.1 KB
scripts/scan_secrets.pyscript11.9 KB
scripts/scan_skill_threats.pyscript102.4 KB
scripts/scan_splitstream.pyscript29.5 KB
scripts/scan_yara.pyscript19.7 KB
scripts/session_scan.pyscript54.1 KB
scripts/suppressions.pyscript15.4 KB
scripts/validate_manifests.pyscript13.7 KB
scripts/verify_install.pyscript26.2 KB
scripts/vuln_feed.pyscript31.1 KB
tests/conftest.pyscript13.4 KB
tests/corpus/DEAD_ANCHORS_CORPUS.mdmarkdown2.3 KB
tests/corpus/budgets.jsonconfig5.6 KB
tests/cursor_helpers.pyscript12.6 KB
tests/fixtures/legacy_main_blocks.jsonconfig10.3 KB
tests/fixtures/powershell_verdict_corpus.jsonconfig114.9 KB
tests/golden/parity_mcp_security.jsonconfig17.5 KB
tests/golden/parity_runtime_dynamism.jsonconfig31.7 KB
tests/golden/parity_sast.jsonconfig59.8 KB
tests/golden/parity_secrets.jsonconfig18.8 KB
tests/golden/parity_skill_threats.jsonconfig48.8 KB
tests/parity_corpus.pyscript6.3 KB
tests/powershell_hook.pyscript8.2 KB
tests/report_builders.pyscript5.0 KB
tests/schemas/sarif-schema-2.1.0.jsonconfig109.1 KB
tests/shell_compat.pyscript2.2 KB
tests/test_adjudication_bridge.pyscript832 B
tests/test_adjudication_containment.pyscript1.4 KB
tests/test_adjudication_output.pyscript20.0 KB
tests/test_adjudication_suppressions.pyscript18.7 KB
tests/test_advisory_adjudication.pyscript1.3 KB
tests/test_agent_relay_rules.pyscript7.8 KB
tests/test_aggregate_json.pyscript10.0 KB
tests/test_auto_scan_patterns.pyscript10.5 KB
tests/test_benign_corpus.pyscript16.4 KB
tests/test_benign_new_scanners.pyscript6.1 KB
tests/test_build_output_skip.pyscript10.6 KB
tests/test_capability_ledger.pyscript18.8 KB
tests/test_codex_install.pyscript10.0 KB
tests/test_codex_marketplace.pyscript3.3 KB
tests/test_comment_false_positives.pyscript2.2 KB
tests/test_composer_dependencies.pyscript4.0 KB
tests/test_compromised_versions.pyscript51.2 KB
tests/test_context_gate.pyscript32.4 KB
tests/test_coverage_status.pyscript7.6 KB
tests/test_css_compounding_shrink.pyscript20.8 KB
tests/test_cursor_adapter.pyscript7.8 KB
tests/test_cursor_benign.pyscript3.4 KB
tests/test_cursor_degrade.pyscript12.7 KB
tests/test_cursor_install.pyscript17.1 KB
tests/test_cursor_latency.pyscript7.2 KB
tests/test_cursor_parity.pyscript5.8 KB
tests/test_cursor_redteam_fn.pyscript4.9 KB
tests/test_cursor_tamper_modify.pyscript14.2 KB
tests/test_cursor_wiring.pyscript32.3 KB
tests/test_d1_yara_correlation.pyscript9.2 KB
tests/test_dead_anchors_extract.pyscript7.6 KB
tests/test_dead_anchors_probe.pyscript19.7 KB
tests/test_evidence_engine_parity.pyscript8.1 KB
tests/test_evidence_model.pyscript11.4 KB
tests/test_forensics_core.pyscript79.2 KB
tests/test_fp_hardening_r3.pyscript9.7 KB
tests/test_fp_hardening_r4.pyscript18.8 KB
tests/test_fp_regression_pairs.pyscript62.5 KB
tests/test_fp_structural.pyscript21.2 KB
tests/test_freshness.pyscript6.2 KB
tests/test_frontmatter_validity.pyscript7.0 KB
tests/test_gpg_rce_hotfix.pyscript4.8 KB
tests/test_hook_inert_data.pyscript6.1 KB
tests/test_hook_scripts.pyscript14.0 KB
tests/test_inspection_cpu_budget.pyscript11.6 KB
tests/test_ioc_manager.pyscript55.4 KB
tests/test_kernel_privesc_rules.pyscript27.8 KB
tests/test_legit_precision_regressions.pyscript6.8 KB
tests/test_lethal_trifecta.pyscript20.7 KB
tests/test_manifest_signature.pyscript1.5 KB
tests/test_manifest_validity.pyscript2.9 KB
tests/test_monotonic_trust_e2e.pyscript4.4 KB
tests/test_non_breaking_contract.pyscript22.7 KB
tests/test_openclaw_install.pyscript6.6 KB
tests/test_pack_parity.pyscript24.8 KB
tests/test_parse_pnpm_lock.pyscript10.7 KB
tests/test_plugin_checkout_provenance.pyscript11.1 KB
tests/test_powershell_hook_wire.pyscript10.6 KB
tests/test_powershell_verdict_corpus.pyscript6.2 KB
tests/test_pr44_hardening.pyscript6.5 KB
tests/test_pre_scan.pyscript19.6 KB
tests/test_pre_scan_composer.pyscript7.4 KB
tests/test_precondition_fields.pyscript4.6 KB
tests/test_provenance_offline.pyscript2.5 KB
tests/test_published_rulepack_feed_current.pyscript1.4 KB
tests/test_py38_compat.pyscript3.3 KB
tests/test_pypi_pinned_versions.pyscript19.3 KB
tests/test_pyproject_string_forms.pyscript2.2 KB
tests/test_redteam_fn_regression.pyscript32.5 KB
tests/test_reflective_fetch_execute.pyscript23.5 KB
tests/test_reflective_review_fixes.pyscript17.8 KB
tests/test_refresh_controller.pyscript19.9 KB
tests/test_refresh_rulepacks.pyscript12.4 KB
tests/test_review_gate_regressions.pyscript9.3 KB
tests/test_rule_loader.pyscript23.2 KB
tests/test_rulepack_feed.pyscript38.1 KB
tests/test_run_forensics_json.pyscript1012 B
tests/test_run_scanner_fail_loud.pyscript6.5 KB
tests/test_runtime_floors.pyscript19.8 KB
tests/test_sandbox_probing_rules.pyscript9.6 KB
tests/test_sarif_export.pyscript19.9 KB
tests/test_scan_agent_skills.pyscript31.3 KB
tests/test_scan_archive.pyscript11.6 KB
tests/test_scan_ast.pyscript12.8 KB
tests/test_scan_binary.pyscript15.3 KB
tests/test_scan_bytecode.pyscript21.5 KB
tests/test_scan_dast.pyscript32.1 KB
tests/test_scan_dataflow.pyscript7.1 KB
tests/test_scan_dead_anchors.pyscript11.5 KB
tests/test_scan_decode.pyscript28.0 KB
tests/test_scan_dependencies.pyscript37.8 KB
tests/test_scan_devcontainer.pyscript8.5 KB
tests/test_scan_entropy.pyscript11.2 KB
tests/test_scan_entrypoint.pyscript19.5 KB
tests/test_scan_git_config.pyscript58.5 KB
tests/test_scan_git_config_review_fixes.pyscript33.3 KB

tests/test_cursor_latency.py

View on GitHub
"""Latency ceiling for the Cursor blocking path — PRD v3 §5.6 row 7 (O7). P1.

beforeShellExecution sits in the agent's inner loop: every shell command waits
on it. A gate that is merely correct but slow gets uninstalled, so the budget
is a contract, not an aspiration.

MEASURED at M0 on the reference machine (Python 3.10, warm page cache), whole
process including interpreter startup:

    clean command (no finding)   median 18.3 ms   p95 26.9 ms
    IOC path (loads the feed)    median 24.8 ms   p95 32.0 ms
    in-process decision only     median  0.003 ms

Almost all of the wall time is `python` starting up, which is why the shipped
"<10ms" figure refers to the detection itself and is met with three orders of
magnitude to spare.

Ceilings below are set well above the reference numbers on purpose. This is a
regression alarm, not a benchmark: shared CI runners are routinely 3-5x slower
and vary run to run, and a test that fails on a noisy neighbour teaches people
to rerun until green. What it must catch is a change that puts real work on
this path — an unbounded subprocess spawn, a scanner import, a network call — which would
blow past these numbers by an order of magnitude, not a few milliseconds.

Methodology follows the eval review's flakiness note: discard warmup runs, take
N samples, assert on the MEDIAN (a single p95 sample on shared CI is a coin
flip), and carry a relative check that is immune to how slow the host is.
"""

import json
import os
import statistics
import time
from pathlib import Path

import cursor_helpers as ch
import pytest

WARMUP = 3
SAMPLES = 15

# Absolute ceilings (milliseconds, whole process incl. interpreter startup).
#
# Scaled on Windows, and not by a guess: this repo already carries a Windows-only
# CI failure of exactly this kind -- test_session_scan.py::TestLatency asserts
# `< 300ms` and measured 453ms on a shared windows-latest runner while ubuntu and
# macOS passed. Python process startup there is several times the POSIX cost
# before any of our code runs, and a shared runner adds variance on top.
#
# Adding a Windows job (this PR does) while keeping POSIX-tuned wall-clock
# assertions would import that same flake into a second workflow. The absolute
# numbers are a coarse "did someone put real work on this path" alarm; the guard
# that actually has teeth is the host-independent ratio check below, plus the
# structural invariants in TestBlockingPathDoesNoRealWork.
_WINDOWS = os.name == "nt"
_SCALE = 4 if _WINDOWS else 1

CLEAN_MEDIAN_CEILING_MS = 400 * _SCALE
IOC_MEDIAN_CEILING_MS = 600 * _SCALE

# The Cursor adapter must not cost meaningfully more than the Claude one: they
# run the same detector behind the same interpreter, so any real gap is the
# adapter doing work it should not. Host-speed independent.
ADAPTER_OVERHEAD_RATIO = 2.5


def _sample(fn, warmup=WARMUP, samples=SAMPLES):
    for _ in range(warmup):
        fn()
    timings = []
    for _ in range(samples):
        start = time.perf_counter()
        fn()
        timings.append((time.perf_counter() - start) * 1000.0)
    return timings


def _report(name, timings):
    return (f"{name}: median={statistics.median(timings):.1f}ms "
            f"min={min(timings):.1f}ms max={max(timings):.1f}ms n={len(timings)}")


class TestBlockingPathLatency:
    def test_clean_command_median_under_ceiling(self):
        timings = _sample(lambda: ch.run_cursor(ch.make_cursor_stdin("git status")))
        median = statistics.median(timings)
        assert median < CLEAN_MEDIAN_CEILING_MS, _report("clean", timings)

    def test_ioc_path_median_under_ceiling(self):
        """The IOC feed load is the slowest legitimate branch."""
        timings = _sample(lambda: ch.run_cursor(
            ch.make_cursor_stdin("npm install keyv@6.0.0")))
        median = statistics.median(timings)
        assert median < IOC_MEDIAN_CEILING_MS, _report("ioc", timings)

    def test_cursor_adapter_costs_no_more_than_claude(self):
        """Host-independent guard: same work, same wire, comparable cost."""
        cursor = statistics.median(_sample(
            lambda: ch.run_cursor(ch.make_cursor_stdin("git status"))))
        claude = statistics.median(_sample(
            lambda: ch.run_claude(ch.make_claude_stdin("git status"))))
        assert cursor < claude * ADAPTER_OVERHEAD_RATIO + 50, (
            f"cursor adapter overhead: cursor={cursor:.1f}ms claude={claude:.1f}ms")


class TestBlockingPathDoesNoRealWork:
    """The structural half of the budget. Timings drift with the host; these
    invariants are what actually keep the path fast, and they fail loudly the
    moment someone adds a scanner import or an unbounded subprocess to the gate."""

    def test_gate_inspects_without_spawning_a_process(self, monkeypatch):
        """Inspection stays in the hook process and never executes payloads."""
        import subprocess
        import sys
        import pre_scan
        raw = json.dumps(ch.make_cursor_stdin('echo benign'))
        def inspect(argv, **kwargs):
            pytest.fail('the gate must not spawn an inspection process')
        monkeypatch.setattr(pre_scan.hook_adapter, 'read_stdin', lambda **kw: raw)
        monkeypatch.setattr(sys, 'argv', [pre_scan.__file__, '--adapter', 'cursor'])
        monkeypatch.setattr(subprocess, 'run', inspect)
        with pytest.raises(SystemExit) as stopped:
            pre_scan.main()
        assert stopped.value.code == 0
        assert 'os.system' not in Path(pre_scan.__file__).read_text(encoding='utf-8')

    def test_hook_adapter_is_a_leaf_module(self):
        """hook_adapter must import nothing from the repo. If it grew a
        dependency on forensics_core, the blocking path would start paying for
        the whole scanner framework's import cost."""
        import hook_adapter
        source = Path(hook_adapter.__file__).read_text(encoding="utf-8")
        for forbidden in ("forensics_core", "rule_loader", "ioc_manager",
                          "auto_scan", "_shared_patterns", "_context_gate"):
            assert f"import {forbidden}" not in source, (
                f"hook_adapter must stay a leaf; it now imports {forbidden}")

    def test_in_process_decision_is_microseconds(self):
        """Excludes interpreter startup, which is the part we do not control."""
        import hook_adapter
        import pre_scan
        payload = json.dumps(ch.make_cursor_stdin("git status"))

        def once():
            request = hook_adapter.parse_request("cursor", payload)
            pre_scan.decide(request.command)

        timings = _sample(once, warmup=200, samples=2000)
        median = statistics.median(timings)
        assert median < 1.0, _report("in-process decision", timings)

    @pytest.mark.parametrize("cmd", ["git status", "echo hi", "ls -la"])
    def test_non_matching_commands_never_load_the_ioc_feed(self, cmd):
        """The fast path must stay fast: a command that matches no install
        pattern must not touch the IOC database at all."""
        import pre_scan
        loaded = []
        original = pre_scan.check_ioc_packages
        pre_scan.check_ioc_packages = lambda *a, **k: loaded.append(1) or []
        try:
            pre_scan.decide(cmd)
        finally:
            pre_scan.check_ioc_packages = original
        assert not loaded, f"{cmd!r} reached the IOC loader on the fast path"
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall