LLM Mart Basic

Hunting skill for business logic vulnerabilities. Built from 12 public bug bounty reports. Covers coupon-race-stacking (Instacart, Stripe, Reverb), negative-quantity-in-cart price tampering (Upserve, Eternal/Zomato), decimal/fraction price-field overflow (Shipt), client-side chec

Hunting skill for cache poison vulnerabilities. Built from 10 public bug bounty reports including X-Forwarded-Host poisoning, X-HTTP-Method-Override / GCS cache, reflected→stored XSS via cache, classic Omer-Gil Web Cache Deception, Cloudflare Cache Deception Armor bypass, session

Hunt CAPTCHA Bypass — 6 distinct patterns: (1) CAPTCHA field simply omitted from the request (server-side validation absent), (2) CAPTCHA token replayed from a solved challenge (no single-use enforcement), (3) CAPTCHA response accepted on a different endpoint than it was solved o

Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terra

Hunt Clickjacking — missing X-Frame-Options / CSP frame-ancestors lets an attacker embed the target page in an invisible iframe and trick victims into clicking buttons they cannot see (UI redressing). Targets: login flows, money transfers, account settings, OAuth confirmation pag

Hunt cloud / infrastructure misconfigurations. AWS: public S3 buckets (s3:GetObject anonymous), permissive bucket policies (PutObjectAcl public-write), exposed CloudFront origin, public Lambda function URL, public RDS snapshot, IAM credentials in JS bundles, AWS metadata accessib

Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs prefix-only), pre-flight (OPTIONS) gating bypass, postMessage origin checks. High only when an attacker-controlled origin can perform a CREDE

Hunting skill for csrf vulnerabilities. Built from 15 public bug bounty reports including modern variants — SameSite=Lax sibling-subdomain bypass (Argo CD CVE-2024-22424), GraphQL mutations-via-GET (GitLab $3,370), framework-wide CSRF middleware disabled (Stripe Dashboard $5,000)

Hunt Insecure Deserialization — Java gadget chains (ysoserial), PHP object injection (phpggc), Python pickle RCE, .NET BinaryFormatter, Ruby Marshal.load, JNDI/Log4Shell. RCE via deserialization is almost always Critical. Use when target runs Java, PHP serialization, Python pickl

Skill-set loader for /hunt orchestrator. Fingerprints the target, picks the right platform attack skills, and loads the Red Team or WAPT skill set. Use when /hunt has just received a mode answer (redteam or wapt + blackbox|greybox) and needs to load the appropriate skills and pri

Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin check), Service Worker abuse (intercept requests from same-origin script), CSS Injection/Exfiltration (attribute selectors → token char-by-char v

Hunt mishandling of exceptional conditions — feed an endpoint malformed/unexpected input (wrong type, broken JSON, oversized field, null byte) and make it fail OPEN or leak internals: a verbose stack-trace / framework error page that discloses ORM internals, server file paths, li

Hunt file upload bugs — RCE via webshell, XSS via SVG/HTML, SSRF via XXE in DOCX, path traversal via filename. Bypass tables (10 techniques): double extension (shell.php.jpg if server checks last ext only), magic bytes spoofing (PNG header on PHP), null byte (shell.php0.jpg), cas

Hunt fintech-specific GraphQL vulnerabilities: money-movement mutations (transfers, redemptions, withdrawals, card top-ups), ledger/balance/portfolio query IDOR, decimal-precision and rounding abuse, idempotency-key bypass enabling double-spend, KYC/PII field-level authorization

Hunt Forgot Password / Account Recovery Authentication Flaws — 5 distinct patterns: (1) username enumeration via different responses for valid vs invalid email, (2) reset token exposed directly in the API response body, (3) reset token not invalidated after use (replay), (4) pass

Hunting skill for graphql vulnerabilities. Built from 12 public bug bounty reports across IDOR via node() / GID, mutation IDOR including AI/LLM features, cross-tenant IDOR, SSRF via argument, batching-DoS, query-cost-bypass, SQLi via argument, broken-object-level-authz, auth-bypa

Hunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication / metadata-stripping on internal endpoints, plaintext gRPC over HTTP/2, internal endpoint disclosure, proto file leakage, gRPC-Web/grpc-gateway transcoding injection, an

Hunt Host Header Injection — password reset poisoning → ATO, web cache poisoning via unkeyed Host/X-Forwarded-Host, routing-based SSRF (Host picks upstream → cloud metadata/internal services), path-override SSRF/ACL-bypass (X-Original-URL/X-Rewrite-URL), OAuth redirect_uri/issuer

Hunt HTML Injection — user-supplied input is rendered as raw HTML in the response without sanitisation, allowing an attacker to inject arbitrary HTML tags (but not necessarily JavaScript). Lower severity than XSS but enables phishing, UI manipulation, and credential harvesting vi

Hunt HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where one request ends and the next begins (Content-Length vs Transfer-Encoding header parsing inconsistency). CL.TE: front-end uses CL, back uses TE → smuggle by send

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.

`crabbox shard` forks a [checkpoint](checkpoint.md) into `--count` leases

`crabbox share` grants other people access to an existing lease through the

`crabbox ssh` resolves a lease and prints a ready-to-run `ssh` command for it.

`crabbox status` prints the current state of a lease: its slug, provider,

`crabbox stop` ends a single lease. For coordinator-backed and direct cloud

`crabbox sync-plan` prints the local sync manifest and its size hotspots

`crabbox tunnel` opens one foreground SSH local port-forward to a resolved

`crabbox unshare` removes sharing rules from a coordinator-backed lease. It is

`crabbox usage` reports lease cost and usage estimates from the broker, broken down by user, organization, or the whole fleet.

`crabbox verify` checks a signed run receipt produced by `crabbox run --attest`.

`crabbox vnc` prints (or opens) the connection details for a desktop-capable

`crabbox warmup` leases a box and waits until it is ready: it provisions (or

`crabbox watch` runs a command on a warm lease, then watches the local

Linux portal viewers default to **Match window**: only the connected controller

`crabbox whoami` calls the broker's `/v1/whoami` endpoint and prints the

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.

{{SKILL_ENTRY:decision-lifecycle}}

Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.

Lightweight Q&A about the project — answer from context and return, no routing, no state change.

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

Agent OS: the agent gets smarter on its own. We just hold the line: the grading command and expected result never make it into the success contract we hand it.…

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

:memo: Vimlike Modal Text Editor in Rust

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

Hermes Agent memory plugin/provider for scope-aware recall, SQLite truth, LanceDB semantic search, and hybrid retrieval.

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式，带到每一个 AI 工具里。

A coding agent: give it a prompt and it reads, writes, runs commands, and searches code in a loop until the work is done, using native tool-calling across OpenA…

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and…

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

DeepSeek Harness Desktop (dsh-desktop). EAC: Embracing All Creation (揽尽万象). Bundled Node.js runtime with full dsh-CLI kernel, one-click startup, 10 built-in UI…

See your agent think. Zero-config observability & governance for 26 AI agent runtimes: Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Cline, Ope…

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP…

Yet another coding agent harness, lightweight and written in go.

a coding Agent from pi. ∞ providers, sub-agents, hashline edits, and a permission gate

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting…

🧠 Leon is your open-source personal assistant.

The Station, an open-world multi-agent environment that models a miniature scientific ecosystem.

The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

VelaTerm = iTerm2 + Codex, The Best Terminal for AI Coding