Identify and exploit vulnerabilities in the AI Supply Chain by injecting malicious models, datasets, or dependencies. Use this skill to simulate advanced persistent threats (APTs) compromising Hugging Face repositories, manipulating pre-trained weights (Model Poisoning), and exploiting insecure deserialization during model loading (e.g., Pickle files).
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。
Perform forensic analysis of the macOS Unified Logging System (ULS) to investigate system events, application crashes, kernel panics, and potential indicators of compromise (IoCs) such as persistence mechanisms or unauthorized access.
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。
Exploit Mass Assignment vulnerabilities in APIs and web frameworks to inject unauthorized parameters. This skill details how attackers uncover hidden fields and manipulate JSON or HTTP bodies to elevate privileges or tamper with data logic.
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。
Exploit an application's absolute trust in its underlying LLM (Overreliance). Use this skill to induce critical "hallucinations" (confident falsehoods) that cause downstream logical systems or automated agents tracking the LLM's output to make destructive actions or grant unauthorized access.
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。
Network protocol attack playbook. Use when exploiting layer 2/3 protocols including ARP spoofing, LLMNR/NBT-NS/mDNS poisoning, WPAD abuse, DHCPv6 attacks, VLAN hopping, STP manipulation, DNS spoofing, IPv6 attacks, and IDS/IPS evasion.
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。
Use when testing APIs and web frameworks for mass assignment vulnerabilities where user-controlled request body fields are bound directly to model attributes without a field allowlist. Trigger on: ORM update/create endpoints, REST APIs accepting JSON body, Rails strong parameters, Django model forms, Laravel fillable/guarded, Node.js Mongoose/Sequelize, PUT/PATCH requests, registration endpoints, profile update endpoints, GraphQL mutations. Detects privilege escalation via role/admin/isAdmin fields, plan upgrades via subscription fields, and horizontal access via ownerId/userId injection.
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。
Identify and exploit logical flaws in OAuth 2.0 and OpenID Connect workflows. Use this skill when testing "Sign in with Google/Facebook/Apple" features, focusing on Authorization Code interception, Implicit flow token leakage, standard CSRF bypassing via missing `state` parameters, and redirect logic flaws.
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。
Perform static reverse engineering and analysis on Windows Portable Executable (PE) files to identify malicious indicators without executing the file. Use this skill during Incident Response, malware triage, or threat hunting to safely extract metadata, imported APIs, exported functions, embedded strings, and packed indicators from suspicious Windows binaries (.exe, .dll, .sys).
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。
Exploit PHP object serialization vulnerabilities (Insecure Deserialization). This skill details how to identify unserialize() injection points and construct malicious serialized objects using Property Oriented Programming (POP) chains to achieve Remote Code Execution (RCE).
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。
Exploit path traversal and local/remote file inclusion (LFI/RFI) via URL parameters, cookies, and hidden fields using ../ sequences, URL encoding (%2e%2e%2f), double encoding (%252e%252e%255c), Unicode bypasses (..%c0%af), and Windows UNC paths. PHP include/require with $_GET/$_POST/$_COOKIE pattern. Target /etc/passwd, boot.ini, web.config. Tools: DotDotPwn, WFuzz, Burp Suite, ZAP.
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。
Internal network assessment. VLAN hopping, ARP spoofing detection, broadcast protocol abuse (LLMNR/NBT-NS/mDNS), network segmentation verification, SNMP enumeration, NFS exposure, router/switch audit, and internal service mapping. Assumes attacker has network access. Uses nmap, arp-scan, nbtscan, snmpwalk, onesixtyone, smbmap, nfs-common, masscan, hping3, and netexec.
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。
Full penetration test using MCP tools — recon, scanning, exploitation, and reporting. Tailored for OpenCode (BYO LLM). Supports network/web targets and local codebases. Chains into analyze-cve, threat-modeling, and remediate skills automatically.
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。
Exploit weak password reset and change flows via CSRF on reset forms, cross-user password modification by swapping username parameters, token predictability in reset links, reset displaying old password in plaintext (revealing weak storage), missing current-password verification on change forms, and session hijacker lockout via passwordless change. Test with Burp Suite, OWASP ZAP following OWASP Forgot Password Cheat Sheet.
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。
Execute lateral movement within Active Directory environments using credential material (NTLM hashes and Kerberos tickets) instead of plaintext passwords. Use this skill when engaging in red team operations or internal network penetration tests to expand access, bypass authentication portals, and achieve Domain Dominance without relying on crackable passwords.
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。
Path traversal and LFI playbook. Use when file paths, download endpoints, include operations, archive extraction, or wrapper behavior may expose filesystem control.
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。
Plan and execute authorized phishing and social engineering campaigns for red team engagements. Use this skill when conducting simulated social engineering attacks including email phishing, spear phishing, vishing, pretexting, and credential harvesting. Covers GoPhish setup, pretext development, payload delivery, and measuring human vulnerability. Requires explicit written authorization before any testing.
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。
Identify Open Redirect vulnerabilities where applications route users to arbitrary external URLs based on unvalidated input. Prove maximum impact by chaining Open Redirects with OAuth token theft, SSRF, or Phishing, graduating this typically low-risk finding into a high-severity report.
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。
Logs the outcome of a skill execution to observations/<skill-name>/runs.md. Trigger on: "log this run", "skill worked", "skill failed", "this didn't work", "log the outcome", "record this", "note that", or after any skill completes with a clear success, partial, or failure outcome. Creates the observations file if it does not exist, then appends an entry with date, task description, skill used, outcome, what worked, what failed, and any error messages observed.
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。
Open redirect playbook. Use when URL parameters, form actions, or JavaScript sinks control navigation targets and may redirect users to attacker-controlled destinations.
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。
Exploit AI applications using Indirect Prompt Injection. This skill focuses on hiding malicious instructions within data sources (web pages, documents, emails) that the LLM processes, causing the AI to execute unintended actions or leak data without direct user interaction.
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。
Deep OAuth 2.0 / OpenID Connect security assessment. Covers the full attack surface: redirect_uri validation bypass (path traversal, open redirect chains, subdomain confusion, URL parsing tricks, parameter pollution, response mode switching), missing/broken state parameter CSRF, PKCE downgrade and absent-challenge attacks, implicit grant token leakage (Referer, browser history, XSS fragment theft), authorization code injection, scope escalation, client confusion attacks, mutable-claims account takeover (iss+sub confusion, email-keyed identity merging), pre-account takeover via unverified registration, OpenID Connect dynamic client registration SSRF (logo_uri, jwks_uri, sector_identifier_uri, request_uri), nonce replay, ID token validation failures, Device Code phishing flow, mobile custom URI scheme hijacking, refresh token persistence, token introspection enumeration, consent screen clickjacking, host header injection, and cross-IdP mix-up attacks. Uses KOAuth, jwt_tool, nuclei oauth templates, and manual http(action="request", ...) payloads. Every technique includes actual request payloads and verification logic. Chains from /pentester or /api-security when OAuth endpoints are discovered. Chains into /web-exploit for open redirect, XSS, and SSRF chaining. Chains into /post-exploit when full account takeover is achieved. Chains into /credential-audit when access tokens or refresh tokens are recovered.
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。
Comprehensive LLM security testing prompts for bias detection, data leakage, alignment testing, and adversarial prompt resistance.
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。
Complete PortSwigger deep-dive with exact payloads for every lab variant including zero-day techniques
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。
Deep OSINT reconnaissance using the MITRE ATT&CK Reconnaissance framework. Email harvesting with SMTP verification, subdomain takeover detection, certificate transparency mining, Shodan/Censys intelligence, Wayback Machine historical analysis, social media profiling, cloud storage enumeration, document metadata extraction, DNS history, credential leak checks, and passive infrastructure mapping. Uses theHarvester, amass, dnsrecon, fierce, dnstwist, dmitry, whatweb, wafw00f, exiftool, metagoofil, smtp-user-enum, swaks, waybackurls, subfinder, and crt.sh. Pure reconnaissance — no active exploitation. Produces: confidence-scored findings, infrastructure diagram, employee roster, email pattern confirmation, subdomain takeover candidates. Chains into /pentester for active testing.
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。