threat-profile

threat-profile is a skill for Claude Code from MingyiSecLab/Mingyi-Atlas. It costs 36 tokens per session (1,022 once invoked), scanned A, original, Apache-2.0.

A threat-actor profiling guide for planning realistic adversary simulations. It helps describe an attacker, their skill level, likely entry methods, and behaviors using MITRE ATT&CK, a common map of attack techniques.

In plain words
What is it for?
It is for researching APT groups, choosing an attacker sophistication level, and creating profiles for vulnerability assessments, penetration tests, red-team exercises, or insider-threat scenarios.
Why use it?
It prevents a red-team exercise from becoming a random collection of tools and actions. The engagement can instead imitate a defined type of attacker.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It is for researching APT groups, choosing an attacker sophistication level, and creating profiles for vulnerability assessments, penetration tests, red-team exercises, or insider-threat scenarios.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mingyiseclab/mingyi-atlas/threat-profile
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.

Any agent
npx skills add MingyiSecLab/Mingyi-Atlas --skill threat-profile
Clone the repo
git clone --depth 1 https://github.com/MingyiSecLab/Mingyi-Atlas

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for threat-profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/threat-profile/github.svg)](https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/threat-profile)
Your own site
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/threat-profile"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/threat-profile/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for threat-profile

Your own site · 80×15
<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/threat-profile"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/threat-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,022 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.01022
Opus 5 $0.00018 $0.00511
Sonnet 5 $0.00007 $0.00204
Haiku 4.5 $0.00004 $0.00102

Measured 9d ago against content hash aac65f05a5b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

threat-profile 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 9d ago.

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.

src/skills/standard/soundwave/threat-profile/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.

Threat Profile Builder

Threat profiling defines who the red team is emulating. Without a clear profile, the engagement devolves into arbitrary tool usage instead of realistic adversary simulation.

When to Use

  • During CONOPS creation when selecting a threat actor
  • User asks about threat actors, APT groups, or adversary emulation
  • Need to map engagement scope to realistic attacker behaviors

Workflow

Step 1: Determine Tier

Ask the user which tier fits. If they're unsure, recommend based on engagement type:

Tier Actor Type Sophistication Best For
1 Opportunistic attacker Low Vulnerability assessment, external scan
2 Targeted cybercriminal Medium Penetration test, focused engagement
3 APT / nation-state High Full red team, advanced simulation
4 Insider threat Varies Internal assessment, assumed breach

Step 2: Build the Profile

Gather or derive these fields — see references/adversary-archetypes.md for pre-built profiles and references/apt-groups.md for known APT group details:

  1. Name/Alias — Known group or custom archetype
  2. Sophistication — low / medium / high / nation-state
  3. Motivation — financial, espionage, disruption, hacktivism
  4. Initial Access — MITRE technique IDs for how they get in
  5. Key TTPs — Top 5-10 MITRE ATT&CK techniques
  6. Tools & Infrastructure — Realistic toolset for this actor

Step 3: Validate Against RoE

The profile must be consistent with what the RoE allows. There's no point emulating spearphishing if social engineering isn't authorized.

RoE Constraint Profile Implication
External only, no social engineering Focus on T1190, T1595, T1133
Phishing authorized Include T1566, T1598
Internal assumed breach Start from T1078 (Valid Accounts)
Full red team Full kill chain TTPs

Step 4: Output

Generate two payloads:

(a) Standalone plan/threat-profile.json — full ThreatProfile schema:

Read the full file on GitHub · 84 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 84 lines · 36 tokens per session scan A aac65f05a5b8

Subscribe to this mod's changes

threat-profile is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,022 once invoked, about $0.0002 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 2026-09-03.