apt29-cozy-bear

apt29-cozy-bear is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 63 tokens per session (5,314 once invoked), scanned A, original, Apache-2.0.

An adversary-emulation profile describing APT29, a Russia-attributed cyber-espionage group, and the intrusion techniques associated with it.

In plain words
What is it for?
Planning controlled red-team exercises around APT29-style techniques, especially attacks involving cloud services, identities, and Microsoft 365.
Why use it?
It gives an authorized security team a defined threat model for testing whether defenses detect and respond to this kind of activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Planning controlled red-team exercises around APT29-style techniques, especially attacks involving cloud services, identities, and Microsoft 365.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/apt29-cozy-bear
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,482 stars · on GitHub · decepticon.red

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 PurpleAILAB/Decepticon --skill apt29-cozy-bear
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

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 apt29-cozy-bear

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/apt29-cozy-bear/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/apt29-cozy-bear)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt29-cozy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt29-cozy-bear/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 apt29-cozy-bear

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt29-cozy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt29-cozy-bear.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,314 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to critical

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • critical YARA Match · line 120
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • high YARA Match · line 73
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • high Privilege Escalation · line 76
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 86
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high YARA Match · line 110
    YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
    Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
How audits are shown
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 $0.00063 $0.05314
Opus 5 $0.00032 $0.02657
Sonnet 5 $0.00013 $0.01063
Haiku 4.5 $0.00006 $0.00531

Measured 11d ago against content hash 1c5d1ab693ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

apt29-cozy-bear 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 11d 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.

packages/decepticon/decepticon/skills/shared/adversary-emulation/apt29-cozy-bear/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APT29 (Cozy Bear, Midnight Blizzard, NOBELIUM, The Dukes) — Adversary Emulation Profile

APT29 (MITRE ATT&CK G0016; also tracked as Cozy Bear, Midnight Blizzard, NOBELIUM, The Dukes, CozyDuke, UNC2452, Dark Halo, NobleBaron, YTTRIUM, Blue Kitsune, IRON RITUAL/IRON HEMLOCK) is a Russian state-sponsored cyber-espionage group attributed by multiple governments to Russia's Foreign Intelligence Service (SVR). Active since at least 2008, it is among the most operationally disciplined intrusion sets on record: it favors patient, stealthy, long-dwell access against high-value strategic targets, custom and living-off-the-land tooling, rigorous operational security (residential-proxy infrastructure, anti-forensic indicator removal, low-and-slow authentication attacks), and a sustained pivot toward cloud and identity-plane attacks (Microsoft 365 / Entra ID, OAuth, federation). It is best known for the 2015–2016 DNC intrusion, the 2020 SolarWinds Orion supply-chain compromise, and the 2024 Microsoft corporate-email breach. This profile teaches Decepticon to emulate APT29's signature TTPs so an authorized red team can exercise the blue cell against a realistic, identity-and-cloud-centric espionage adversary.

Attribution & motivation

  • Suspected sponsor / nation: Russian Federation — Foreign Intelligence Service (Sluzhba Vneshney Razvedki, SVR). Attribution is publicly asserted by the U.S. government (CISA/FBI/NSA), the UK NCSC, Canada's CSE, and corroborated by vendor reporting (Mandiant/Google, Microsoft, CrowdStrike).
  • Motivation: Strategic espionage — collection of foreign-policy, diplomatic, defense, government, and technology intelligence in support of Russian state interests. APT29 is not financially motivated and is not primarily a destructive actor; its goal is durable, covert access and exfiltration of intelligence, not disruption.
  • Confidence: High for SVR attribution — it is the consensus of multiple Five Eyes governments and independent commercial vendors, reinforced by consistent tradecraft across a decade-plus of operations.

Read the full file on GitHub · 148 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. 11d ago First seen · 148 lines · 63 tokens per session scan A 1c5d1ab693ef

Subscribe to this mod's changes

apt29-cozy-bear is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 63 tokens to every session and 5,314 once invoked, about $0.0003 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 2026-08-30.