Pular para o conteúdo
Novo

DeepSeek V4.1 Flash grátis por 7 dias: 10M tokens por dia após recarga de $10 ou mais. Até 30/11.

Como funciona
aeondave/ai-ml-ctfIA, agentes e MCP

ai-ml-ctf

⁨Lab/CTF: AI/ML challenges; model artifacts, checkpoints, embeddings, LoRA, classifiers, model APIs, RAG/tool-use, adversarial ML.⁩

v2026.11.13-21cd5683 instalações+3 em 7 dias39 EstrelasMITsincronizado há 10 horas

Instalar

Ainda não tem a CLI da NotHoly? Instale primeiro.

$ curl -fsSL https://notholy.com/install.sh | sh
$ notholy skills install aeondave/ai-ml-ctf

Grava em ⁦~/.notholy/skills⁩ depois de conferir a assinatura e o SHA-256.

AssinaturaAssinado, ed25519
UuPLdOVmLB…i9MnqHDA==A CLI confere o SHA-256 e a assinatura antes de gravar qualquer arquivo.
Pacotef551ef8a…f8b953ba
f551ef8acb56…a3b1f8b953ba5 arquivos · ⁦26.4 KB⁩
VarreduraAlto17 achados
  • injection.ignore_instructionsreferences/adversarial-ml.md:336
  • injection.ignore_instructionsreferences/llm-attacks.md:18
  • injection.ignore_instructionsreferences/llm-attacks.md:30
Ver a varredura completa
Fontegithub.com/AeonDave/malskill/tree/main/offensive-ctf/ai-ml-ctf@21cd568

Este item ainda não foi escrito no seu idioma, então aparece em English.

Goal: solve AI and machine-learning CTF tasks with artifact-first triage, controlled experiments, and reproducible evidence.

When this skill applies

  • model files, checkpoints, embeddings, LoRA adapters, classifiers, serialized pipelines, feature extractors, or model APIs
  • adversarial examples, model inversion, extraction, poisoning, membership inference, or prompt-injection tasks
  • LLM tool-use, RAG, context, or guardrail bypass puzzles in authorized challenge environments

Operating model

  1. Classify the dominant lane: model artifact, training data, feature pipeline, inference API, LLM app, RAG/tool flow, or embedded model.
  2. Define the oracle: target class, recovered secret, membership decision, extracted weights, prompt leak, tool action, or checker response.
  3. Load the closest methodology before selecting tools.
  4. Load only the reference matching the lane; do not run every attack family by habit.
  5. Build a controlled local reproduction or differential query harness before claiming a model weakness.
  6. Record parameters, seeds, prompts, inputs, outputs, confidence, and exact validation proof.

Technique integration

Primary methodology to load:

  • web-exploit-technique
  • llm-technique
  • vuln-research for vulnerability hypotheses and reproducible findings
  • reversing-technique
  • python-patterns
  • python-testing

Use these as decision engines. This skill adds challenge-oriented triage, experiment design, and reference routing for AI/ML tasks.

Tool routing

Prefer these tool families when the corresponding signal appears:

  • python-patterns
  • python-testing
  • langchain-py
  • pytorch
  • keras
  • scikit-learn
  • vec2text
  • jwt-tool
  • mitmproxy
  • frida
  • ghidra

Tool syntax belongs in the tool skills. This skill decides when a tool family fits and what output should validate progress.

Evidence patterns

  • Favor artifact-first triage, shortest reproducible path, and explicit validation signal before pivoting.
  • Record failed hypotheses with evidence so an agent does not repeat expensive dead paths.
  • Prefer category-specific tools after surface classification instead of running every attack family by habit.
  • End with a replayable proof: recovered secret, local verification, model output delta, extracted artifact, or correlated evidence chain.

Category-specific quick pivots

  • Classify artifact first: model checkpoint, serialized pipeline, REST endpoint, LLM application, or feature-extraction code.
  • Use differential queries and local reproduction before assuming a model weakness.
  • For LLM tasks, separate prompt-layer bypass from tool/RAG injection and validate with controlled probes.
  • For checkpoints, inspect format, framework, architecture, tensor names, metadata, and unsafe deserialization risk before loading.
  • For adversarial examples, pin preprocessing, normalization, epsilon/constraint, target class, and success metric.
  • For extraction/inversion, record query budget, input basis, confidence/logit access, and surrogate validation.
  • For LoRA/adapter tasks, inspect adapter config, rank, alpha, target modules, merge math, and prompt/template assumptions.

Quality gates

  • No claim without a validation signal: recovered secret, replayed exploit, decoded artifact, reproduced model behavior, or corroborated evidence.
  • Do not brute force before representation, constraints, and success oracle are known.
  • Keep a pivot ledger: hypothesis, evidence, result, next shortest path.
  • Keep challenge/platform/competition names out of notes and generated reports.
  • Never load untrusted pickle/joblib checkpoints in the main environment; inspect metadata or load in a throwaway sandbox when required.
  • Distinguish stochastic variance from a real exploit by repeating with fixed seeds or multiple trials.

Resources

  • references/adversarial-ml.md — adversarial examples, patch attacks, evasion, poisoning, and backdoor detection workflows.
  • ART — load when implementing an experiment with ART estimator adapters or attack/evaluation APIs; keep the challenge's existing success oracle.
  • references/llm-attacks.md — prompt injection, jailbreaks, token smuggling, context manipulation, tool-use, and RAG/task-flow attacks.
  • references/model-attacks.md — model inversion, extraction, membership inference, LoRA merging, checkpoint arithmetic, and encoder collisions.
  • references/model-file-forensics-and-deserialization.md — Load for model-file artifacts: format triage, safe pickle/opcode inspection, deserialization RCE sinks (pickle, Keras Lambda, GGUF SSTI, ONNX), and secret recovery from weights/metadata.

Arquivos desta versão

Permissões

PermissãoDeclaradaEncontrada na varredura
Lê arquivosSimSim
Grava arquivosSimSim
Roda comandos no shellSimSim
Usa a redeSimSim
Usa conectoresSimSim
Controla um navegadorNãoNão

Achados da varredura

Revisado em 13 de nov. de 2026

  1. AltaPrompt injection · injection.ignore_instructionsreferences/adversarial-ml.md:336
  2. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:18
  3. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:30
  4. AltaPrompt injection · injection.system_promptreferences/llm-attacks.md:30
  5. AltaPrompt injection · injection.system_promptreferences/llm-attacks.md:36
  6. AltaPrompt injection · injection.chat_markupreferences/llm-attacks.md:36
  7. AltaPrompt injection · injection.system_promptreferences/llm-attacks.md:39
  8. AltaPrompt injection · injection.system_promptreferences/llm-attacks.md:85
  9. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:126
  10. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:132
  11. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:162
  12. AltaPrompt injection · injection.ignore_instructionsreferences/llm-attacks.md:354
  13. AltaPrompt injection · injection.system_promptreferences/llm-attacks.md:354
  14. MédiaPrompt injection · injection.no_confirmationreferences/adversarial-ml.md:620
  15. MédiaPrompt injection · injection.role_overridereferences/llm-attacks.md:147
  16. MédiaLink · Link para um IP diretoreferences/llm-attacks.md:410
  17. InfoLink · Links para domínios externos

Uma varredura limpa reduz o risco, mas não prova que o pacote é seguro. Leia o que você instala.

VersãoPublicada emCommitSHA-256AssinaturaMudança de permissão
v2026.11.13-21cd56813 de nov. de 202621cd568f551ef8aAssinada–

Pergunte tudo o que o seu escopo permite.

Crie a conta, adicione créditos e faça a primeira pergunta no chat ou no terminal.

  1. 1/3

    Crie a conta

    Individual ou empresa. Dá para virar empresa depois sem perder saldo nem chaves.

    Pessoa físicaEmpresa
  2. 2/3

    Adicione créditos

    No cartão. Você paga por token, sem assinatura.

    $5.00recarga mínima
  3. 3/3

    Pergunte

    No chat, ou instale o CLI e rode notholy login no terminal.

    $ notholy login