Identifies and unpacks packed binaries: detecting packers from section names and entropy, automatically unpacking UPX, and manually unpacking custom packers by finding the OEP and dumping. Activates for requests to unpack a packed sample, detect a packer, or recover the original binary from UPX or a custom packer.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Do not use generic unpackers as a guarantee — modified UPX and custom packers defeat
upx -d. Fall back to debugger-based manual unpacking.
upx for standard UPX; x64dbg + Scylla for manual unpacking (see the x64dbg skill).python scripts/analyst.py detect sample.bin
Signals: section names (UPX0/UPX1, .aspack, .themida), high section entropy, a tiny
import table, and a small .text with a large high-entropy section.
If standard UPX:
upx -d -o sample_unpacked.bin sample.bin
If upx -d fails on a UPX-like sample, the header was likely tampered (e.g. UPX! magic or
version bytes altered) — repair the marker or unpack manually.
In x64dbg: break on VirtualAlloc/VirtualProtect, run until the unpacked region is written
and made executable, find the tail jump to the original entry point (OEP), and dump there.
Use Scylla to dump the process and reconstruct the Import Address Table (IAT) so the dumped PE loads in a disassembler.
Confirm the dump is a clean PE with a populated import table and readable strings/code.
.text drops to normal code levels.upx -d on tampered UPX and concluding it is not UPX; check for renamed/edited
markers.references/api-reference.md for the packer detector.まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Reverses Android malware: unpacking APKs, decompiling DEX bytecode to readable Java, auditing the manifest for abused permissions and components, and locating dynamically loaded or native payloads. Activates for requests to analyze an APK, decompile DEX, or investigate a suspicious Android app.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes API call traces from a sandbox or API monitor (JSON) to group calls by category, reconstruct high-level behaviors (process injection, file drops, network, crypto), and flag suspicious call sequences. Activates for requests to analyze an API trace, interpret sandbox API logs, or identify behavior from Win32/Native API calls.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes Windows Authenticode signatures on PE files: checking for a signature, reading the signer certificate chain, detecting revoked/expired/stolen certs, and recognizing signature-stripping and catalog-signing abuse. Activates for requests to analyze a code signature, verify Authenticode, or assess signer trust on a PE.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes banking trojan webinject configurations to extract targeted institutions, injected JavaScript/HTML, and data-theft hooks, mapping the fraud workflow. Activates for requests to analyze banking trojan webinjects, parse a webinject config, or map targeted banks and credential-theft injections.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes Python-based malware packaged as PyInstaller/py2exe executables by detecting the packer, locating the embedded archive, and identifying bundled .pyc modules for extraction and decompilation. Activates for requests to analyze compiled Python malware, unpack a PyInstaller binary, or extract pyc modules from a frozen Python executable.
日本語の概要は準備中です。原文の説明を表示しています。
Analyzes cryptojacking/coinminer malware by extracting mining pool endpoints (stratum), wallet addresses, algorithm and miner identifiers (XMRig and forks), and persistence or resource-control settings from static strings and config. Activates for requests to analyze a cryptominer, extract mining pool and wallet IOCs, or identify coinminer configuration.
日本語の概要は準備中です。原文の説明を表示しています。