LLM Mart Basic

Hunting skill for idor vulnerabilities. Built from 26 public bug bounty reports. Use when hunting idor on any target.

Hunt JWT cryptographic failures — alg:none signature-stripping and RS256→HS256 key-confusion that let an attacker forge a token for any identity (e.g. an admin) without knowing a secret. Use when the app authenticates with a JSON Web Token (an `eyJ...` Bearer token in the Authori

Hunt Kubernetes & Docker — API anonymous access, kubelet 10250 exec (SPDY/WebSocket, NOT plain POST) and the simpler /run primitive, etcd 2379 unauth, dashboard skip-login, RBAC misconfig, secret/SA-token abuse, docker.sock host escape, runc/container-escape (Leaky Vessels CVE-20

Hunt Laravel specific vulnerabilities — Debug mode leakage (APP_DEBUG=true exposes full stack trace + env vars), Laravel Telescope/Horizon dashboard unauthorized access, Ignition RCE (CVE-2021-3129), Signed URL manipulation, Queue Worker abuse, mass assignment via Eloquent, deser

Hunt LDAP Injection and XPath Injection — authentication bypass, blind char-by-char attribute exfiltration, AD user/group enumeration, XML-store XPath bypass. Covers the LDAP special-character set (* ( ) \ NUL /), search-filter-context vs DN-injection, parenthesis-balancing, AND/

Hunt Local File Inclusion (LFI), Remote File Inclusion (RFI), and Path Traversal — /etc/passwd read, log poisoning → RCE, PHP filter-chain RCE (no upload needed), php:// / data:// / zip:// / phar:// wrappers, RFI via allow_url_include, directory traversal read/write/delete. Cover

Hunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web page

Hunt MFA / 2FA bypass — 7 distinct patterns. (1) MFA not enforced on sensitive endpoints (password change, email change accept without MFA challenge), (2) MFA-step skip via direct navigation to post-login URL, (3) MFA-token replay (same code accepted twice), (4) brute-force the 6

Hunting skill for misc vulnerabilities. Built from 225 public bug bounty reports. Use when hunting misc on any target.

Hunt Next.js specific vulnerabilities — Server Actions arbitrary function execution, Middleware auth bypass via static asset paths, ISR cache poisoning, Image Optimization SSRF (/_next/image), RSC payload leakage, getServerSideProps injection, source map exposure, debug endpoint

Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration, child_process/eval injection, template engine SSTI (EJS/Pug/Handlebars), path traversal in file servers, require() injection, environment variable

Hunt NoSQL Injection — MongoDB operator injection ($where, $regex, $gt, $ne), CouchDB, Redis command injection, auth bypass via NoSQLi, data dump. Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages.

Hunt NTLM/Negotiate information disclosure on internet-reachable IIS/SharePoint/Exchange. Anonymous NTLM Type-2 challenge capture leaks NetBIOS domain, internal DNS forest, computer name, AD timestamp via AV_PAIRS structure. Default Windows-installer hostnames (WIN-XXXXXXXXXXX pa

Hunting skill for oauth vulnerabilities. Built from 19 public bug bounty reports. Use when hunting oauth on any target.

Hunt Open Redirect — all types including low-impact, chained to OAuth token theft → ATO, phishing chains. URL parameter manipulation, JavaScript redirect, meta refresh, header injection. Use when hunting redirect bugs or building ATO chains.

Hunting skill for race condition vulnerabilities. Built from 12 public bug bounty reports including modern HTTP/2 single-packet attack cases (James Kettle DEF CON 2023 "Smashing the State Machine"; RyotaK / Flatt Security 10,000-request first-sequence-sync expansion 2024). Covers

Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vect

Hunting skill for rce vulnerabilities. Built from 67 public bug bounty reports. Use when hunting rce on any target.

Hunt SAML / SSO attacks. Patterns: XML Signature Wrapping (XSW) — modify Assertion while keeping Signature valid by relocating signed element, comment injection in NameID (admin@target.com<!--evil-->@attacker.com → some parsers see admin@target.com), signature stripping (remove S

Hunt Session Management vulnerabilities — session fixation (no regeneration on login), insufficient invalidation on logout / password-change / email-change, predictable or low-entropy session IDs, JWT-as-session with no exp/revocation, refresh-token rotation/reuse-detection gaps,

Fourteen posts of being wrong in production, compressed to checkboxes

Healthy nodes, a quiet network, 300 restarts in three days, and a latency budget measured in milliseconds

Discovery worked. Ping worked. Every TCP connection timed out, and later the tunnel only worked when someone had a terminal open.

Every VM came back. The cluster did not. Declarative systems converge on config, and the datapath isn't config.

A surprising share of AI-in-the-terminal failures aren't the AI. They're zsh, and a version of bash from 2006.

A Claude Code plugin turns standalone project configuration into a namespaced, installable extension that teams and communities can update as one unit.

None of the safety came from the model. It came from six boring habits.

Skills package instructions and references. Subagents run work in a separate context and return results. They solve different problems and can be composed deliberately.

Six hours in, one step left, everything green, and the incident that didn't happen

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

An API request routing a model's tool call through an approval gate to a remote MCP server

31 config keys, two audits, and why the first one was wrong in both directions

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

The most important rule wasn't about what I could change. It was about what I was allowed to display.

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

{{SKILL_ENTRY:refactor}}

{{SKILL_ENTRY:release}}

Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.

Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or {{CMD:feature}}.

Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.

Daily repo hygiene — review the day's repo state, then perform the cleanups under per-action confirmation. Fast-forward only, never destructive without a yes.

Show the project's current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only.

Wire codeArbiter's statusline into ~/.claude/settings.json, or remove it.

The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to open-tasks.md.

{{SKILL_ENTRY:security-architecture}}

{{SKILL_ENTRY:tribunal}}

Watch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.

Copy a file OUT of a running sandbox box to the host — host-initiated egress only (docker cp). The reverse, a host→container bind, is impossible by construction.

Tear down a sandbox box — remove its container and named volume. --keep-volume leaves the volume; with no id, prune reclaims any leaked ca.sandbox=1-labeled object. Cached images are retained.

Run a single command inside a running sandbox box and capture a JSON result — exitCode, separate stdout/stderr, and a truncated flag past the byte cap. The scriptable exec seam.

Open an interactive shell inside a running sandbox box at /work/repo. Read-only root, non-root user, no host-FS access — explore the untrusted code interactively, then exit.

Pull an untrusted repo into an ephemeral, host-FS-isolated Docker container — clone into a named volume, build a dep-cached image, run under structural isolation. Network defaults to offline. Requires Docker and nixpacks.

Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.

Inspect ADR health read-only; optionally select one ADR with --adr N.

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

Unofficial KakaoTalk CLI and native MCP server for macOS — read, watch, and send messages via Accessibility automation.

Local-first AI action assistant for operators: memory, skills, tools, and permission gates to turn work into controlled action.

Agent-driven media library for your cloud drives (Quark 夸克 / 115 / 光鸭 GuangYa / 123网盘 / 天翼 Tianyi)

An open-source desktop AI agent built around Cyrene’s persona and powered by the self-developed Cyrene_Harness framework. It combines immersive character chat w…

在 Android 上运行的 AI 编程 Agent，内置 Linux 终端与代码编辑器，支持 MCP 协议扩展。

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LL…

Floe — a native iOS/iPadOS AI agent workspace for iPhone and iPad, built for private bring-your-own-key workflows.

Spring Boot AI Agent — an out-of-the-box solution that makes your app converse, remember, think, and act.

Give your AI agent eyes for PDFs — structured text, tables, OCR, visual evidence, and page-level citations via MCP. Native Rust, local-first.

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.

Monet — Multi-engine mission control for coding agents (Claude Code and Codex today). Browse, search, and drive your agent sessions from a native desktop app.

A DottedSign MCP server that enables AI assistants (Claude, ChatGPT) to manage signing tasks, templates, and document status via natural language.

Курируемый handbook по Claude Code на русском: hooks, skills, CLAUDE.md шаблоны, MCP-серверы, кейсы.

👾 Open Computer Use – Open-Source Alternative to Codex Computer Use

An open-source AI companion that actually remembers you — runs entirely on your own Mac or server. Desktop pet · long-term memory · proactive companionship · mu…

Graphical management tool for Kubernetes on desktop and mobile.

Open-source desktop app for content creation, with an agent runtime and standalone CLI.

Connect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.

Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.

Open-source native iPhone/iPad client for OpenAI Codex CLI and Claude Code — review diffs, approve actions, steer sessions, and manage Git remotely.