Mythic Profiles logo

Mythic Profiles

Organization
SpecterOps
mythic-profiles

Develop Mythic C2 profiles/listeners and transport containers. Use when designing, implementing, modifying, or validating Mythic C2 profile repositories like MythicC2Profiles, including HTTP/DNS/WebSocket/TCP/SMB-style egress or P2P profiles, C2Profile parameters, server binaries, redirector material, OPSEC checks, and payload-type integration.

Overview

PublisherSpecterOps
Repositoryskills
Skill namemythic-profiles
Stars
706
Forks
80
Bundled files
7
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by SpecterOps on GitHub. Read the source before you install it.

Installation

Install the Mythic Profiles AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/SpecterOps/skills/tree/main/plugins/c2-mythic/skills/mythic-profiles
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/SpecterOps/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/c2-mythic/skills/mythic-profiles .claude/skills/mythic-profiles
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mythic Profiles in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Mythic Profiles on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Mythic Profiles is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Mythic Profiles

Scope

Use this skill for Mythic C2 profile development: profile container layout, C2Profile definitions, parameter modeling, listener/server implementation, P2P versus egress profile decisions, and integration with Mythic payload types.

Use $mythic-implant-development instead when the primary task is implementing an agent/payload type or agent commands. Use this skill when the primary artifact is a C2 profile/listener/transport.

Workflow

  1. Classify the profile

    • Egress profile: server-side code receives agent traffic and forwards to Mythic /agent_message.
    • P2P profile: no listening server; parameters define agent-to-agent connection details.
    • Translation-aware profile: coordinate with a translation container if wire format or crypto differs from Mythic messages.
  2. Set up the development loop

    • Read references/remote-development.md when the task involves local/remote Mythic development, container iteration, or installed-service workflow.
    • Confirm profile folder name, C2Profile name, and Mythic installed service name align.
    • Use focused container restarts and payload-build smoke tests during iteration.
  3. Inspect the repository shape

    • Identify profile language, Docker/container entrypoint, profile definition file, server binary/script, config templates, and any profile-specific utilities.
    • For MythicC2Profiles-style work, treat each top-level profile as a standalone container package.
    • Preserve existing profile naming, parameter names, and build/deploy conventions unless the user asks for a migration.
  4. Define or update profile metadata

    • name: stable profile identifier used by payload types.
    • description, author, semver.
    • is_p2p: False for listener/egress profiles, True for P2P profiles.
    • server_binary_path: executable/script that handles traffic for egress profiles.
    • server_folder_path: folder exposed in Mythic UI for server-side files/config.
  5. Model C2 parameters

    • Include operator-facing parameters such as callback host/port, interval, jitter, headers, bind address, URI paths, proxy settings, or peer connection fields.
    • Use verifier_regex for format-sensitive values.
    • Use crypto_type=True for Mythic-managed crypto parameters such as AES/HMAC profile keys.
    • Prefer parameter names the payload build function can consume directly through get_parameters_dict().
  6. Implement listener/server behavior

    • Accept or receive the profile transport format.
    • Extract the Mythic agent message.
    • Forward to Mythic’s /agent_message endpoint.
    • Return Mythic’s response in the profile’s transport format.
    • Add bounded config validation, useful logs, and no secret-bearing debug output.
  7. Integrate with payload types

    • Ensure payload types list the profile name in c2_profiles / supported C2 profiles.
    • Confirm the build function embeds or serializes selected profile parameters into agent configuration.
    • Keep agent wire format and profile server expectations synchronized.
  8. Validate

    • Confirm container starts and syncs with Mythic.
    • Confirm profile appears in payload build UI.
    • Build a test payload with the profile selected.
    • Confirm checkin, get-tasking, post-response, file transfer, and error paths as applicable.
    • Document exact commands, config values changed, and validation evidence.

Reference loading

Read only what is needed:

  • references/developer-series.md for routing based on the Mythic for Developers playlist topics.
  • references/profile-development.md for implementation patterns, profile file anatomy, and validation checklist.
  • references/remote-development.md for local/remote container iteration and installed-service workflow.
  • references/third-party-service-profiles.md for profiles that broker traffic through external services such as chat/storage/webhook APIs.
  • ../mythic-implant-development/references/c2-profile-definition.md for detailed C2Profile class and parameter examples.
  • ../mythic-implant-development/references/agent-message-format.md when the transport wraps Mythic agent messages.
  • $mythic-translation-containers when profile behavior depends on custom message formats or crypto.
  • ../mythic-implant-development/references/p2p-connections.md for SMB/TCP-style P2P routing.

Output requirements

For design/review tasks, return:

  • profile type: egress, P2P, or translation-aware
  • files changed or files to create
  • parameter schema and operator-visible defaults
  • server/listener data flow
  • payload-type integration points
  • validation commands/checks
  • risks, assumptions, and unresolved profile-specific questions

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mythic Profiles AI skill do?

Develop Mythic C2 profiles/listeners and transport containers. Use when designing, implementing, modifying, or validating Mythic C2 profile repositories like MythicC2Profiles, including HTTP/DNS/WebSocket/TCP/SMB-style egress or P2P profiles, C2Profile parameters, server binaries, redirector material, OPSEC checks, and payload-type integration.

Why use Mythic Profiles on TypingMind?

Because you install it once and use it with any model. Mythic Profiles is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Mythic Profiles in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/SpecterOps/skills/tree/main/plugins/c2-mythic/skills/mythic-profiles. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mythic Profiles?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Mythic Profiles?

As many as you like. As long as a model supports skills, you can use Mythic Profiles with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Mythic Profiles AI skill free?

Yes. It is published on GitHub by SpecterOps under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇