インフラ・DevOpsのスキル

Serverless GPU compute platform for AI model deployment — web endpoints, GPU functions, model serving, and TypeScript client patterns

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。

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation

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。

LLM observability with Langfuse — OpenTelemetry-based tracing, evaluations, prompt management, datasets, and production best practices

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。

Replicate SDK patterns for TypeScript/Node.js -- client setup, predictions, streaming, webhooks, file handling, model versioning, deployments, and training

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。

Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint

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。

LiteLLM proxy server setup, TypeScript client patterns via OpenAI SDK, model routing, fallbacks, load balancing, spend tracking, virtual keys, and production deployment

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。

Hugging Face Inference SDK patterns for TypeScript/Node.js — InferenceClient setup, chat completion, text generation, streaming, embeddings, image generation, audio transcription, translation, summarization, and Inference Endpoints

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。

Prepare logical commits, publish through Pharos’s protected-main pull-request gate, monitor deployment, and hand off operational acceptance. Use only when commit, push, publish, release, or deployment watching is requested.

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。

Diagnose and fix failed Pharos GitHub Actions, adaptive PR checks, Cloudflare deploys, Pages releases, or scheduled automation. Use when a gate/run failed or the user asks to retrigger and iterate until clear.

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 adding, reviewing, squashing, deploying, or rolling back Pharos D1 migrations or schema cleanup.

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 hosting, deploying, or operating an app on the Prisma Platform: projects, branches, preview environments, services and their versions, Prisma Postgres databases, object-store buckets, environment variables, custom domains, logs, or the GitHub integration. Triggers on "Prisma Platform", "Prisma Compute", "Prisma Postgres", "Prisma Storage", "preview environment", `prisma deploy`, `prisma dev`, `prisma auth`, `prisma project`, `prisma branch`, `prisma service`, `prisma postgres`, `prisma bucket`, `prisma git`, `prisma.config.ts`, promote, rollback.

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。

Server-Side Request Forgery (SSRF) occurs when user-controlled input is used to construct URLs that the server fetches, enabling access to internal services, cloud metadata endpoints (169.254.169.254), and local files via `file://` scheme. Detect via parameters accepting URLs or hostnames, PDF/report generators rendering `<iframe>/<img>/<script>`, and blind SSRF via out-of-band DNS callbacks. Bypass filters using IP decimal/octal/hex encoding, URL-userinfo tricks, and URL fragments. Tools: Burp Collaborator, curl.

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。

SSRF playbook. Use when the server fetches URLs, resolves hostnames, imports remote content, or can be driven toward internal networks, cloud metadata, or secondary protocols.

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 Server-Side Request Forgery (SSRF) vulnerabilities in applications hosted on AWS to access the highly sensitive Instance Metadata Service (IMDS). This allows an attacker to steal valid IAM roles and temporary security credentials, leading to catastrophic cloud account compromise.

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。

Sandbox escape playbook. Use when breaking out of Python sandbox, Lua sandbox, seccomp filter, chroot jail, container/Docker, browser sandbox, or namespace isolation to achieve unrestricted code execution or file 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。

Deploy an Evil Twin (Rogue Access Point) to clone a legitimate Wi-Fi network's SSID and MAC address. By combining this with targeted deauthentication attacks, an attacker aggressively forces nearby victims to silently connect to the malicious AP, enabling pervasive Man-in-the-Middle (MitM), captive portal phishing, and credentials interception.

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 logic flaws in OAuth implementations, focusing specifically on the absence or improper validation of the `state` parameter, which leads to Cross-Site Request Forgery (CSRF) and account takeover (ATO).

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。

Detects sensitive data stored insecurely on mobile devices (Android/iOS). Trigger on: SharedPreferences, NSUserDefaults, SQLite, Room DB, DataStore, Core Data, Keychain misconfiguration, external storage, backup exposure, plaintext files, unencrypted databases, adb backup, iCloud backup, NSFileProtection, EncryptedSharedPreferences, SQLCipher, allowBackup, FLAG_SECURE, keyboard cache, sensitive logs. Covers MASVS-STORAGE-1 (local storage) and MASVS-STORAGE-2 (exposure to unauthorized actors).

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。

HTTP/2 protocol-specific attack playbook. Use when the target supports HTTP/2 and you need to exploit binary framing, HPACK compression, h2c upgrade smuggling, pseudo-header injection, stream multiplexing abuse, or H2→H1 downgrade translation 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。

Exploit misconfigured Kubernetes Role-Based Access Control (RBAC) to escalate privileges within a cluster. This skill covers identifying overly permissive roles and bindings, and leveraging them to gain cluster-admin access or compromise the host nodes.

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。

Escape from Docker containers to the host system using container misconfigurations, mounted sockets, privileged mode, capabilities abuse, and kernel exploits. Use this skill when testing containerized environments for breakout vulnerabilities during penetration tests. Covers Docker socket mounting, cgroup escapes, nsenter techniques, and Kubernetes pod escapes.

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 misconfigured Docker environments, specifically focusing on privilege escalation via an exposed Docker daemon socket (`docker.sock`) or membership in the local `docker` user group to achieve root access on the host system.

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 Server-Side Request Forgery (SSRF) vulnerabilities in applications hosted on AWS EC2 instances to extract IAM credentials and User Data from the Instance Metadata Service (IMDS). This skill covers techniques for bypassing basic filters to access IMDSv1 and concepts of IMDSv2.

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。