mcp2agy-exploit

An exploit-development coordinator that turns confirmed vulnerabilities and security building blocks into working exploit scripts. It covers memory-corruption, web and API, authentication, logic, and multi-step exploit scenarios.

In plain words
What is it for?
It coordinates exploit work involving ROP, heap bugs, use-after-free, SSRF, SSTI, SQL injection, deserialization, race conditions, privilege escalation, and exploit-chain assembly.
Why use it?
It helps security researchers validate how separate weaknesses could be used together during authorized testing.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/uziii2208/mcp2agy/exploit
Any agent
npx skills add uziii2208/mcp2agy --skill exploit
Clone the repo
git clone --depth 1 https://github.com/uziii2208/mcp2agy

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00087 $0.01024
Opus 5 $0.00044 $0.00512
Sonnet 5 $0.00017 $0.00205
Haiku 4.5 $0.00009 $0.00102

Measured yesterday against content hash cbfbe38eae82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp2agy-exploit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/plugins/mcp2agy/skills/exploit/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/exploit — Exploit Development & Weaponization Engine (v3.0.0)

0. Prime Directive & Operating Model

The Exploit engine turns verified vulnerabilities and security primitives into working, deterministic exploit scripts:

                      ┌───────────────────────────────────┐
                      │   Exploit Orchestrator (/exploit) │
                      └─────────────────┬─────────────────┘
                                        │
        ┌───────────────────┬───────────┴───────────┬───────────────────┐
        ▼                   ▼                       ▼                   ▼
┌───────────────┐   ┌───────────────┐       ┌───────────────┐   ┌───────────────┐
│ Memory Corrupt│   │ Web & API Bug │       │ Logic & Auth  │   │ Exploit Chain │
│ (pwntools/ROP)│   │ (SSRF/SSTI/..)│       │ (Race/PrivEsc)│   │ Assembler     │
└───────────────┘   └───────────────┘       └───────────────┘   └───────────────┘
        │                   │                       │                   │
        └───────────────────┴───────────┬───────────┴───────────────────┘
                                        ▼
                      mcp2agy_workspace/exploits/
                      ├── pocs/<target>_<cwe>.py
                      ├── payloads/
                      └── chains/<chain_id>_full_rce.py

1. Exploit Categories & Tooling

1.1 Memory Corruption Exploitation

  • Stack & Heap Exploits: Buffer overflows, heap chunk consolidation, fastbin/tcache poisoning, Use-After-Free (UAF).
  • Modern Mitigations: ASLR defeat via info leak, DEP/NX bypass via ROP/JOP gadget chains, Stack Canary bypass.
  • Tools: pwntools, angr, z3-solver, GDB with pwndbg / gef.

1.2 Web & Application Layer Exploits

  • Command & Code Injection: Shell escape breakout, argument injection, double-quoted context differentials (_pde).
  • Server-Side Template Injection (SSTI): Jinja2, Mako, FreeMarker, Pug, Handlebars sandboxed environment escapes.
  • SSRF to Cloud Metadata: AWS IMDSv1/v2, GCP metadata headers, internal Kubernetes service tokens.
  • Insecure Deserialization: Java ysoserial chains (CommonsCollections, Spring), Python pickle / yaml gadgets, PHP object injection.

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 84 lines · 87 tokens per session scan A cbfbe38eae82

Subscribe to this mod's changes

mcp2agy-exploit is a skill published in the GitHub repository uziii2208/mcp2agy (1 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,024 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens