Commit Graph
47 Commits
Author SHA1 Message Date
a1b5d51a8d feat(go): inspect embedded binary build metadata (#1363)
* feat(go): inspect embedded binary build metadata

* fix(go): preserve byte metadata and validate container mappings

* fix(go): support moduleless legacy build metadata

Recognize optional module string headers in declared zero-filled memory while rejecting ambiguous and unmapped pointers. Preserve the original module-pointer field as the zero-byte source anchor.

Classify initial symlink-loop and overlong-path failures as invalid input, with CLI and MCP regressions.

* fix(go): reject undersized PE optional headers

* fix(native): stabilize ELF memory checks and clean up exec wrappers

Use existing parent/group/run-token ownership for caller-selected Python launchers, which can exec through a shell or prlimit. Add cancellation regressions for the valid wrapper and wrong-parent/token cases.

Replace the timing-dependent 30,000-section memory workload with a valid 32 MiB padded ELF under a 64 MiB address-space limit. Check the same image successfully through CLI and MCP before requiring a typed memory failure, preserving the production timeout and all error assertions.

Validation: npm run check and check:fast passed; 61 focused tests passed including Go CLI/MCP and session snapshots. Real decoder probes with pinned packages passed on Python 3.12.3 and 3.12.14. The full local ELF verifier is blocked by this container's procps/process-ownership boundary; the exact pushed head requires GitHub's real-binary-layout lane.

* test: repair Electron fixtures and stabilize catalog startup checks

Declare Electron imports in option, preload override, and path-resolution fixtures after upstream began requiring proven API provenance. Retain all option and preload assertions and adjust exact source ranges for the added import line.

Use the existing bounded acceptance timeout for the cold catalog lifecycle test instead of a separate 15-second ceiling. This retains the coverage allowance and all catalog, error, and cleanup assertions without retries.

Validation: npm run check, final check:fast, formatting and diff checks passed. Source path regression and Go boundary/MCP/service checks passed. All 20 Go CLI cases and both supported-host runtime cases passed on rerun; two macOS-only cases skipped on Linux. A prior contended local run timed out once in a Go CLI diagnostic; that case passed on rerun. Electron process-boundary verification is blocked locally by procps namespace inspection and requires fresh CI.

* test(mcp): isolate nested schema references between tool contracts

Clear Ajv's non-meta schema registry after each root, including compilation failures. Disabling root registration alone leaves nested IDs available to later tools and can let a dangling reference pass the catalog gate.

Add regressions for leakage after successful and failed compilation while retaining shared meta-schema validators. The regression failed before the fix; all 11 schema cases and full npm run check pass. Reviewed independently.

* test(ci): align Go effects and source-map verification contracts

Audit the Go inspector wording as static metadata inspection. Assert retained source declaration indexes in BOM reconstruction and the compiler-derived nested-map oracle. Keep a 45,000-map admission control below the 32 MiB output budget and the 50,000-map overflow case above it with the expanded representation.

Validation: reproduced all four failing assertions, then passed 120 focused tests and the final admission suite. npm run check and real Chrome 154 / esbuild 0.25.10 source-map verification passed, including all four nested-map scenarios and verified process lineage.

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-12 11:34:02 +08:00
morluto b38429cb6a fix(native): preserve universal Mach-O container identity
Keep FAT container format distinct from selected slice architecture through target admission, Evidence, snapshots, and CLI/MCP lifecycle results. Preserve native, Hopper, Ghidra, extraction, and dylib routing for the Mach-O family.

Reject selected FAT ranges overlapping their table or too short for a Mach-O header. Replace empty-slice fixtures with in-bounds executable headers and cover thin, universal, single-slice, FAT64, and swapped containers.

Validation: static and architecture checks, generated docs, targeted producer and public MCP tests. Provider routing uses controlled fixtures; no live Hopper, IDA, JADX, or Ghidra analysis was performed for this change.
2026-10-12 09:29:07 +08:00
6395e8d300 perf(mcp)!: compact repeated session discovery facts (#1988)
Group repeated session tool availability and provider capability facts, preserve complete named contracts and ordered limitations, and remove duplicate catalog descriptors. Update consumers and migration guidance.

Validated by all 31 CI jobs, focused source checks, and actual Claude Code/Linux Hopper/native Windows Ghidra small-target workflows on the current integration tree.

Refs #723.

BREAKING CHANGE: binary_session no longer includes server_identity.catalog.tools; tool_availability and provider capabilities use grouped facts documented in docs/mcp-contracts.md.

Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com>
2026-10-12 07:40:19 +08:00
Itoje DollarandGitHub e4ac7bbfc2 fix: order remaining outputs independently of host locale (#1867)
* fix: order remaining outputs independently of host locale

String.prototype.localeCompare without a pinned collation follows the
host's ICU default locale, so the same input could be ordered differently
on different machines. 614fb768 moved canonical domain projections to
compareUnicodeCodePoints; provider, application, catalog, and setup
orderings still used locale collation.

Order every remaining source site by Unicode code point, including Mach-O
symbols, firmware extraction paths, ASAR entries (previously pinned to
"en" collation), evidence ID sets, browser and Electron target, script,
and resource inventories, reconstruction obligations, capability and
provider listings, and setup environment details.

The current tool and prompt catalog names order identically under both
comparators, so the catalog identity digest is unchanged.

* fix(artifacts): order ASAR entries by their portable path

@electron/asar lists host-spelled paths, so code-point order over the raw
spelling still differed by host: "a\b" sorts after "a0" on Windows while
"a/b" sorts before it on POSIX. Pair each listing with its portable
archive path once, order by that path, and keep the host spelling for
@electron/asar calls and adapter keys.
2026-10-12 01:10:01 +08:00
ffaf2c12f1 feat(wasm): inspect local artifacts with WABT (#1533)
* feat(wasm): inspect local artifacts with WABT

* fix(wasm): preserve custom names and failed cleanup ownership

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-11 19:49:00 +08:00
749e58772a feat(jeb): add JEB engine provider over its MCP interface (#1536)
* feat(jeb): add JEB engine provider over its MCP interface

Add a bring-your-own JEB provider that serves project, unit, and
decompilation inspection from a caller-started JEB client speaking MCP
(streamable HTTP, selected with REA_JEB_MCP_URL). Expose four provider-neutral
operations through shared CLI/MCP workflows: inspect_jeb_client,
open_jeb_project, list_jeb_units, and decompile_jeb_item, each returning
Evidence with engine identity, endpoint, and preserved refusal reasons.

The adapter keeps JEB's envelope semantics: success fields are parsed
format-aware at the boundary, message-only refusals become unsupported-target
errors with the engine's own reason, transport failures become availability
failures with recovery guidance, and unit pagination derives coverage from the
engine's 100-item page cap. Explicit unknowns (implicitly selected unit,
omitted filters) are reported instead of guessed.

Verified against a real JEB 5.48.0 licensed build serving jeb-mcp-server 1.3.0
headless: client inspection, unit listing, and method decompilation were
exercised through the CLI, MCP boundary, and scripts/verify-jeb.mjs.
JEB 5.48.0 headless instances do not advertise open_project; the refusal is
preserved and documented.

* fix(jeb): verify against a real signed APK and fix CLI option surface

Verify the provider against a locally built, v1/v2/v3-signed probe APK
(binary manifest, classes.dex with a launcher activity) on JEB 5.48.0: the
full unit tree (apk, manifest, three certificate units, dex bytecode,
decompiler), wildcard-filtered and paginated unit listing with derived
coverage, parent-restricted listing, and launcher-activity method
decompilation through both CLI and MCP, including dexdec's inline
constant folding of the probe's obfuscated tag.

Move list-jeb-units filter/pagination and decompile-jeb-item unit selection
from positional arguments to options; the MCP schemas are unchanged.

* fix(jeb): preserve engine refusals through the real MCP boundary

Testing against the published Signal 8.30.3 universal APK exposed a boundary
bug the scripted provider tests missed: decodeJebToolResult raised a protocol
error for isError results before the provider could map JEB's
{success:false, message} envelope, so real engine refusals surfaced as
unreadable output instead of the engine's own reason. Decode refusal
envelopes like any structured result and let the provider preserve the
reason; cover the decoder directly, including contentless and unparseable
results.

Signal verification: full 109 MB R8/Kotlin/Compose APK with four signature
schemes and native arm64 ELF units parsed; MainActivity.onCreate and R8
synthetic lambdas decompiled through CLI and MCP; paginated, filtered, and
parent-restricted unit listing; refusal path confirmed on the live engine.

* docs(jeb): record Flutter Gallery verification on the real-engine lane

Verify the provider against the official Flutter Gallery 2.9.2 release APK
(112 MB): per-ABI libapp.so Dart AOT snapshot images analyzed as native code
with 75k methods on arm64, snapshot internals and wrapper methods decompiled
through both CLI and MCP with explicit unit selection, decoded manifest, and
filtered native-library unit discovery. Note that JEB 5.48.0 headless does
not expose the dedicated Dart snapshot processor or run_script; both remain
GUI-only engine surfaces.

* docs(jeb): translate the README JEB row for every supported language

The JEB row was inserted in English across all translated READMEs; each now
carries its own label, capability summary, requirements, and guide link
following that language's Android-row conventions.

* fix(jeb): enforce local endpoints and preserve cancellation

* fix(jeb): refuse redirects across the local MCP boundary

---------

Co-authored-by: REA Contributor <contributor@rea.tools>
Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 23:03:27 +08:00
ded59689ce fix(javascript): accept the Wakaru 1.x release line and verify 1.14.0 (#1540)
* fix(javascript): accept the Wakaru 1.x release line and verify 1.14.0

Exact --version equality rejected every Wakaru build except 1.13.0, and
strict report schemas rejected any added field, so each upstream release
broke recovery until REA re-pinned. Wakaru now documents that --version,
--json and provenance.json change only by addition within a major version.

Admit ^1.13.0 with the verified/compatible split used for Binwalk and
Unblob, report the observed version instead of the pinned constant, and
add a limitation for unverified releases. Parse reports with loose
objects and keep the reported module status as a string; path, identity,
range and file-set checks stay exact.

Move the audited pin, submodule, CI binary and verifier to 1.14.0, and
document where to get the binary from the refusal message.

* fix(javascript): project known Wakaru warning fields

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 23:02:15 +08:00
905e4866c4 feat(artifacts): inspect PE resource identities and payload ranges (#1482)
* feat(artifacts): inspect PE resource identities and payload ranges

* fix(artifacts): reject header payloads overlapping PE sections

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-10 23:02:06 +08:00
YsopwnableandGitHub 636b245f1b fix(android): support owned JADX stdio on Windows (#1276)
Support owned JADX stdio on Windows x64, preserve protocol input errors through cancellation, and verify native stdin and Android CLI/MCP lifecycle on the real Windows host.

Closes #1262
2026-10-09 20:34:42 +08:00
Kaoru0822andClaude Opus 5.5 cf77d073fc fix(session): require an open target for session-bound native and artifact tools
binary_session reported native and artifact operations available whenever
their provider declared them, although these operations run on the active
target: in a closed session every call failed with target_unavailable, and
Mach-O-only operations stayed available with a ZIP or ELF target open.

Report target_required for every session-bound contract kind in a closed
session, and target_unsupported for Mach-O-only operations unless the open
target is a Mach-O executable. A host limitation is reported before target
selection, since opening a target cannot fix it; composed operations keep
deciding from their requirements.

Fixes #1166

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 03:02:40 +00:00
morluto c715af8058 fix(android): report actual provider readiness 2026-10-09 07:29:17 +08:00
YsopwnableandGitHub 163ee09a74 feat(native): inspect recorded crashes through pwntools and pwndbg (#1054)
* feat(native): inspect recorded crashes through pwntools and pwndbg

* fix(native): bind core note semantics to raw owner bytes

* fix(native): validate recorded core ABI and evidence scalars

* fix(native): require complete recorded note interpretations

* fix(native): bind physical core notes to original headers
2026-10-08 16:50:31 +08:00
YsopwnableandGitHub 7af7bc88ce feat(evm): inspect offline bytecode interfaces through EVMole (#1051)
* feat(evm): inspect offline bytecode interfaces through evmole

* fix(evm): distinguish unsupported bytecode targets

* style(evm): format verifier string-prefix checks
2026-10-08 15:32:05 +08:00
YsopwnableandGitHub 4fc6565b0f feat(native): inspect offline ELF layout through pwntools (#1037)
* feat(native): inspect offline ELF layout through pwntools

* fix(build): prepare offline ELF verification on clean runners

* fix(native): preserve snapshot acquisition cancellation

* fix(native): handle sectionless ELF and retain decoder diagnostics

* test(native): verify malformed symbol table entry sizes

* fix(native): respect inherited limits and unused segment fields

* fix(native): preserve packed relocations and decoder launch constraints

* fix(native): validate symbol spans and preserve resource failures

* fix(native): preserve diagnostic completeness and memory failures

* fix(native): guard bridge imports against allocation failures

* fix(native): validate relocation symbol and section references

* fix(native): retain diagnostics through compounded cleanup failures

* fix(native): preserve unresolved relocation section references

* fix(native): bound linkage evidence and preserve CPU signal diagnostics

* fix(native): preserve file-size resource failure evidence

* fix(native): retain opaque linkage names and late cancellation output

* test(native): make CPU-limit fixture robust across runners

* fix(native): verify resource failure branches before interpreting exits

* fix(native): validate declared ELF string references

* fix(native): validate section-name table before decoding

* fix(native): enforce canonical ELF name-table escapes
2026-10-08 14:22:08 +08:00
b5afa5f91e feat(browser): attribute native execution and listener sources (#917)
* feat(browser): attribute native execution and listener sources

Integrate finite native precise-coverage windows and direct DOM listener inspection through shared CLI/MCP workflows, exact session script identities, inline source evidence and owned instrumentation cleanup.

Refs #881, #774

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): preserve runtime identity and settle fixture cleanup

Retain complete reported initiator objects, reject changing loader availability, propagate the selected operation through main-frame authorization and complete effect/help inventories. Close only the synthetic owned Chrome via its native endpoint, await process-group settlement and preserve primary verification errors during cleanup.

Refs #881

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): settle invalid events and preserve document evidence

Accept same-document URL changes with proven stable loader identity, retain metadata without inventing ownership, terminate malformed event collection immediately, and sanitize known transport URLs without erasing sourceURL declarations.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): end detached target windows and sanitize coverage identities

Reuse the existing flat-session event matcher, retain prearming termination, and apply the source identity policy to coverage URLs. Add real MCP target-close verification and producer regressions for detachment orderings.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): retain final sample metadata and settle fatal protocol failures

Keep source inventory open through the resetting sample, propagate fatal wire failures without outstanding commands, and check listener collection failures after final document validation.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): require default execution worlds for website attribution

Preserve native context and world metadata without treating same-frame isolated or unknown contexts as website sources. Verify actual Chrome isolated function execution before excluding its coverage, and cover ambiguous world metadata with producer regressions.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): revalidate runtime source joins and selector failures

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

---------

Co-authored-by: morluto <76467478+morluto@users.noreply.github.com>
2026-10-07 21:45:07 +08:00
ysopwnableandGitHub 01be082e9e feat(browser): trace captured website module imports (#879)
* feat(browser): trace captured website module imports

Compose verified exported scripts, inert native import syntax and a narrow
Chromium resolution port. Preserve query/fragment identity, import-map context,
all reported capture candidates and explicit unknown execution. Share named
CLI/MCP contracts and retain native reports, diagnostics and cleanup failures.

Add focused boundary regressions and a real module-loading oracle to the
existing conditional Chrome lane. No captured application code is executed
by module tracing, and no selected website asset is refetched.

Refs #851, #774

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(browser): preserve module contexts and source bindings

Keep capture completeness inline, validate actual source text against its
digest, and separate unsupported URL contexts from malformed input.
Use the importer origin for native module resolution and the selected map
base independently, including mixed HTTP/HTTPS and escaped HTML attributes.

Refs #851, #774

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
2026-10-07 14:59:52 +08:00
N0zoM1z0andGitHub 166dcd21d0 feat(javascript): recover readable modules with Wakaru (#848)
* feat(javascript): recover readable modules with Wakaru

Integrate pinned upstream source behind a typed optional recovery port,
preserve source identity and producer provenance, and publish verified
artifacts for existing JavaScript analysis through CLI and MCP.

Add focused real-tool CI with genuine bundler fixtures and bounded
resource, cancellation, cleanup, schema and packaged-artifact checks.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* fix(javascript): align recovery catalog and browser verification

Share canonical Wakaru provider identity, describe CLI mode options, and
format the new workflow test. Disconnect the real page transport after
its observation readiness progress instead of a fixed delay.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)
Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)

* refactor(javascript): consume the investigation evidence writer

Verify that the SDK recovery handler records complete Evidence through the newly shared investigation owner.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)

* chore(test): account for isolated recovery fixture compilers

* fix(javascript): validate recovery paths before acquiring the engine

Return field-specific invalid_format diagnostics for relative paths and verify compiled CLI/MCP parity even when the optional engine is unavailable.

Assisted-by: Yukari (gensokyo-skills:yukari-boundary-analysis)

Assisted-by: Kogasa (gensokyo-skills:kogasa-surprise-testing)
2026-10-07 12:46:13 +08:00
N0zoM1z0andGitHub 4a6c17ce83 refactor: declare auxiliary capabilities from source (#853) 2026-10-07 12:32:34 +08:00
bef4321afb fix(firmware): accept the verified Binwalk and Unblob release lines (#844)
* fix(firmware): accept the verified Binwalk and Unblob release lines

Exact --version equality rejected every build except Binwalk 3.1.0 and
Unblob 26.6.4, then stored that constant as the observed engine version.
Admit the 3.1 and 26.6 lines, keep the audited build as verified, and
report the banner that actually ran.

* chore(docs): regenerate skill metadata after firmware contract text

docs:check failed because SKILL.md lagged the Binwalk/Unblob release-line
tool descriptions.

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-10-07 12:19:28 +08:00
N0zoM1z0andGitHub be3cfbffdf fix(mcp): isolate optional observation adapter failures (#838) 2026-10-07 11:45:17 +08:00
N0zoM1z0andGitHub 5a7c769692 feat(firmware): integrate Binwalk and Unblob analysis
* feat(firmware): integrate Binwalk and Unblob analysis

* fix(firmware): verify published files and namespace source references

* test(firmware): isolate extractor dependency failure from process cleanup

* fix(firmware): retain actionable report and cleanup diagnostics

* test: assert retained batch output failure diagnostics
2026-10-06 14:16:04 +00:00
N0zoM1z0andGitHub 904d03e987 feat(android): integrate static APK analysis with headless JADX (#738)
* feat(android): integrate static APK analysis with headless JADX

* test(android): include APK tools in explicit effects audit
2026-10-06 12:46:48 +00:00
morlutoandGitHub e07b81649e refactor!: simplify runtime tools and remove replay engines (#572)
* fix(hopper): report unavailable procedure body coverage

* refactor!: simplify runtime tools and remove replay engines

Keep direct inspection, capture, and comparison tools. Bind handlers to named contracts and let agents compose experiments with commands and local fixture servers.

BREAKING CHANGE: Remove controlled replay, Node characterization, finite replay-machine, managed runtime planning, and redundant string-tracing tools. Retire process replay, shims, reactive scenarios, custom checkpoints, and active browser replay and origin-scope inputs.
2026-10-05 21:15:04 +08:00
morlutoandGitHub b5e98915c6 fix(tools)!: simplify direct invocation and harden boundary contracts (#555)
Remove REA permission grants, scope ceilings, approval confirmations, and inert settings. Preserve selected local evidence, accept caller-chosen commands and paths, and report actual runtime failures.

Harden provider results, schema serialization, snapshot evidence binding, archive paths, source maps, native screenshots, managed EH parsing, and cancellation cleanup. Regenerate tool metadata and document direct invocation.

BREAKING CHANGE: Removed permission configuration and policy commands, approval fields, filesystem scope inputs, and fixed confirmation options. Process capture inherits the host environment and accepts command names; callers must refresh tool schemas and migrate removed fields.
2026-10-05 20:16:44 +08:00
morlutoandGitHub 4fbc501121 feat(native): add inspection primitives, dispatch traces and approved UI observation (#500)
* fix(hopper): normalize string-backed addresses and update verification

* feat(native): add inspection primitives, dispatch traces and approved UI observation

* test: prioritize real artifact E2E and captured golden regressions

* fix(process): queue observed output before reactive rendering actions

* test: prune redundant cases and strengthen boundary assertions

* fix(cli): route native value tracing through shared workflows

* test: replace synthetic success with real workflows and captured data

* fix(catalog): separate portable metadata from native host availability
2026-10-04 16:02:36 +08:00
morlutoandGitHub ed933d1893 feat(native): add investigation features (#486)
* feat(native): add UI and dispatch investigation workflows

* feat(ghidra): support macOS host validation

* docs: update native investigation capabilities

* feat(artifacts): decode compiled Interface Builder archives

* feat(ghidra): expose bounded p-code value flow

* test(ghidra): split host and cross-format verification

* fix(verify): follow complete result contracts

* refactor: remove unused authorization and schema helpers

* refactor: remove unused evidence result alias

* fix(ghidra): report jump-table evidence precisely

* fix(verify): align browser scenario fixture schema

* fix(setup): compare parsed client config structurally

* test(ghidra): verify AArch64 jump-table mappings

* fix(ghidra): recover AArch64 byte jump tables

* test(artifacts): verify compiled interface builder archives

* feat(native): trace UI actions through handlers

* fix(tests): update native trace and shutdown fixtures

* fix(verification): diagnose browser scenario failures

* fix(browser): wrap scenario snapshots in capture state

* fix(native): bind and bound investigation workflows

* fix(artifacts): preserve bounded interface builder evidence

* fix(ghidra): enforce admitted hosts and preflight tools

* fix(native): preserve trace cancellation and bounds

* test(application): expect bound analysis target evidence

* fix(native): preserve investigation bounds and cancellation

* fix(application): preserve bundle and unresolved trace evidence

* style(test): format artifact subject fixture
2026-09-30 00:41:05 +08:00
morluto 2f08c7c932 refactor(tools): remove artificial analysis ceilings 2026-09-29 16:29:23 +08:00
morluto 2a6eb41147 refactor(tools): return complete analysis results inline 2026-09-29 14:53:50 +08:00
morluto f55c2b9267 refactor(mcp): simplify tool inputs and inline results 2026-09-29 11:22:00 +08:00
morluto 0d96275b68 refactor: return complete tool results inline 2026-09-29 07:08:46 +08:00
morlutoandGitHub b8a9da0c0f refactor(mcp): make analysis states unrepresentable (#468)
* refactor(config): parse capability settings into exact states

* refactor(runtime): encode replay and process outcomes exactly

* refactor: make analysis states unrepresentable

* refactor(mcp): register canonical schemas with SDK

* fix: preserve capability and catalog invariants

* fix(build): remove stale compiled modules

* fix(replay): update real verifier policy dependency

* fix(package): verify the complete MCP catalog

* fix(test): supply complete replay reload policy

* refactor(contracts): centralize output schema lookup

* refactor(mcp): delegate protocol boundaries to SDK

* fix(browser): approve real source capture

* fix(mcp): preserve catalog guidance
2026-08-10 02:28:11 +08:00
morlutoandGitHub 8f229ede70 feat(electron): add autonomous Electron runtime analysis (#464)
* feat: add autonomous Electron runtime analysis

* feat(electron): add lifecycle and boundary telemetry

* feat(electron): capture runtime boundary evidence

* fix(electron): package boundary hook helper

* feat(electron): report active capture coverage

* fix(electron): account for bring-your-own runtime

* feat(electron): expand agent-owned runtime scenarios

* fix(ghidra): keep fixture credentials out of argv

* perf(test): serialize local test and docs workloads

* fix(electron): harden active runtime capture

* fix(inspector): require exact runtime target authorization

* fix(docs): make managed manifest host independent

* fix(ci): make generated catalog portable

* fix: unblock autonomous command and electron flows

* fix(electron): close popup and detached helper gaps
2026-08-05 19:07:46 +08:00
morlutoandGitHub 51559245d2 Merge pull request #461 from morluto/agent/comprehensive-repository-audit
fix: harden evidence lifecycle and MCP contracts
2026-08-04 03:00:25 +08:00
morluto ede91ff1f0 fix: align aggregate tools with session capabilities 2026-07-29 18:18:31 +00:00
morluto fecddc0549 perf(mcp): reduce cold-start work 2026-07-26 15:02:58 +00:00
morluto 521139d4a5 feat(native): inspect API boundaries with evidence 2026-07-25 14:29:28 +00:00
morluto 035e1144b0 feat(server): advertise available tools dynamically 2026-07-24 13:18:58 +00:00
morluto b906defbff fix(capabilities): expose typed availability codes 2026-07-23 07:09:16 +00:00
N0zoM1z0 f4156d9663 fix(mcp): preserve investigation input policy 2026-07-21 19:51:11 +08:00
morluto 49f1ec14fe fix: remove unused boundary exports 2026-07-18 04:58:54 +00:00
morluto a1a6b4200e feat(windows): define native authority boundary 2026-07-18 04:50:24 +00:00
morluto ee1cd40405 feat(mcp)!: harden contracts and evidence references
BREAKING CHANGE: comparison tools now require session-owned Evidence IDs or approved bundle paths, and structured Evidence results use compact references.
2026-07-16 19:49:58 +08:00
N0zoM1z0andN0zoM1z0 5f66cfd57a feat(dotnet): add managed runtime correlation planning 2026-07-16 20:10:36 +09:00
N0zoM1z0andN0zoM1z0 d86231ad33 feat(application): add isolated JavaScript replay
Expose one plan/execute replay contract through both CLI and MCP with exact source, input, runtime, sandbox, limit, and export commitments.

Run selected ESM and extracted CommonJS/Rspack factories in a disposable Linux x64 Bubblewrap namespace with a content-addressed Node ELF closure, architecture-checked seccomp, delegated systemd cgroup limits, bounded protocol capture, cancellation, and observable cleanup.

Preserve left and right observations as Evidence, derive differential comparisons without erasing unknowns, add optional separately authorized reproducers, and fail closed on stale plans or unavailable host boundaries.

Add source-owned parser, sanitizer, clipboard, denial, timeout, OOM, protocol-forgery, and cancellation coverage; a real Linux verifier and workflow; regenerated catalogs and TypeDoc; and updated the packaged REA analysis skill for the 83-tool inventory.
2026-07-16 15:45:55 +09:00
N0zoM1z0andN0zoM1z0 be76f8090b feat: add web and Electron reverse-engineering workflows 2026-07-14 20:24:12 +09:00
N0zoM1z0 2c1ceabbf1 feat: add passive website reverse engineering 2026-07-14 12:27:13 +08:00
morluto 2722722425 feat(identity): derive MCP surface metadata 2026-07-14 09:51:42 +08:00