Skip to main content
Manusで任意のスキルを実行
ワンクリックで
PurpleAILAB
GitHub クリエイタープロフィール

PurpleAILAB

2 件の GitHub リポジトリにある 351 件の収集済み skills をリポジトリ単位で表示します。

収集済み skills
351
リポジトリ
2
更新
2026-07-12
リポジトリエクスプローラー

リポジトリと代表的な skills

reverser-overview
ソフトウェア開発者

Root pointer for the binary reversing lane. Covers triage, Radare2 fallback, string extraction, packer unpacking, virtualized protectors, symbol risk, ROP, Ghidra deep analysis, and firmware extraction.

2026-07-12
reverser-virtualized-protectors
ソフトウェア開発者

VMProtect, VMP2, Themida, and CodeVirtualizer reversing workflow using Radare2/Ghidra facts and Back Engineering Labs research guidance.

2026-07-12
dfir-overview
その他コンピュータ職

Use to close the Offensive Vaccine loop on the defender side. The Detector agent produces Sigma / YARA rules from offensive operations; this catalog validates those rules against real memory dumps, event logs, and forensic artifacts using Volatility 3, plaso, and sigma-cli. Without this catalog, detection rules are theoretical.

2026-07-04
ics-overview
その他コンピュータ職

Use when the target is an industrial control system or operational technology network running Modbus, BACnet, S7Comm/S7Comm Plus, DNP3, OPC-UA, or any PLC/HMI/SCADA stack. Engagements MUST set RoE flag industrial_safety_critical=true; this catalog gates every write-scope operation behind explicit operator confirmation regardless of HITL middleware.

2026-07-04
mobile-overview
その他コンピュータ職

Use when the engagement target is an Android (APK / AAB) or iOS (IPA) application. Covers static analysis (jadx, apktool, class-dump), dynamic instrumentation via Frida and Objection, SSL-pinning bypass, root/jailbreak detection bypass, deep-link / URL-scheme abuse, exported-component attacks, IPC redirection, WebView vulnerabilities, and biometric / Face ID / Touch ID bypass.

2026-07-04
osint-overview
その他コンピュータ職

Use when the engagement requires passive reconnaissance only — no packets to the target's authoritative infrastructure. Splits off from the Recon agent so bug-bounty and pre-engagement work can run with outbound-only network policy. Maltego, Shodan, Censys, Hunter.io, breach-data lookups, GitHub code search, Wayback Machine archives, certificate transparency, BGP/ASN mapping.

2026-07-04
supply-chain-overview
その他コンピュータ職

Use when the engagement scope includes supply-chain attack simulation — typosquatted package publication, dependency confusion, GitHub Actions secret mining, internal mirror poisoning, OAuth-app impersonation, or vendor portal credential abuse.

2026-07-04
engagement-startup
その他コンピュータ職

Mandatory first-turn startup procedure — checks for existing engagements, resume/new selection, workspace initialization.

2026-06-30
このリポジトリの収集済み skills 312 件中、上位 8 件を表示しています。
cross-chain
ソフトウェア開発者

Auto-loaded by cross-chain-auditor agent during Phase 2. Provides detection patterns for: missing source chain/address validation, replay attacks, message ordering, chain-specific code, finality assumptions. Core artifact: Cross-Chain Message Flow diagram.

2026-02-02
oracle
ソフトウェア開発者

Auto-loaded by oracle-auditor agent during Phase 2. Provides detection patterns for: stale prices, deprecated Chainlink functions, L2 sequencer downtime, decimal mismatches, spot price manipulation, oracle DoS. Core artifact: Oracle Integration Matrix.

2026-02-02
reentrancy
ソフトウェア開発者

Auto-loaded by reentrancy-auditor agent during Phase 2. Provides detection patterns for: CEI violations, cross-function/cross-contract reentrancy, read-only reentrancy, token callback exploits (ERC721/777/1155). Core artifact: State Timeline map.

2026-02-02
access-control
ソフトウェア開発者

Auto-loaded by access-control-auditor agent during Phase 2. Provides detection patterns for: missing modifiers, privilege escalation, tx.origin phishing, OR/AND logic errors, missing two-step transfer. Core artifact: Permission Matrix.

2026-02-02
token
ソフトウェア開発者

Auto-loaded by token-auditor agent during Phase 2. Provides detection patterns for: fee-on-transfer, rebasing tokens, ERC777 hooks, ERC721/1155 callbacks, missing return values, blacklist/pausable, low decimals. Core artifact: Token Compatibility Matrix.

2026-02-02
upgradeability
ソフトウェア開発者

Auto-loaded by access-control-auditor agent during Phase 2. Provides detection patterns for: UUPS/Transparent/Beacon proxy vulnerabilities, storage collision, initialization issues, function selector clashing, upgrade authorization. Core artifact: Proxy Architecture Map.

2026-02-02
lending
ソフトウェア開発者

Auto-loaded by defi-auditor agent during Phase 2 when analyzing lending protocols. Provides patterns for: liquidation logic, interest rate models, collateral management, health factor calculations, bad debt handling. Core vulnerabilities: self-liquidation, precision loss, oracle manipulation, collateral factor attacks.

2026-02-02
vault-erc4626
ソフトウェア開発者

Auto-loaded by defi-auditor agent during Phase 2 when analyzing ERC4626 vaults. Provides patterns for: share/asset conversion, inflation attack mitigations, rounding direction rules, donation attacks. Critical: first depositor attack, virtual shares offset, dead shares burning.

2026-02-02
このリポジトリの収集済み skills 39 件中、上位 8 件を表示しています。
2 件中 2 件のリポジトリを表示
すべてのリポジトリを表示しました