apt28-fancy-bear

apt28-fancy-bear is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 50 tokens per session (6,408 once invoked), scanned A, original, Apache-2.0.

A threat profile describing APT28, a Russian military intelligence cyber-espionage group, and the attack methods associated with it.

In plain words
What is it for?
Use it to plan authorized tests of defenses against credential attacks, phishing, software exploits, malware, influence operations, and disruptive activity.
Why use it?
It gives security teams a documented actor to study instead of testing against an unspecified attacker. The profile links APT28 behavior to MITRE ATT&CK, a catalogue of known attack techniques.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan authorized tests of defenses against credential attacks, phishing, software exploits, malware, influence operations, and disruptive activity.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/apt28-fancy-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 apt28-fancy-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 apt28-fancy-bear

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/apt28-fancy-bear/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/apt28-fancy-bear)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt28-fancy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt28-fancy-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 apt28-fancy-bear

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt28-fancy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt28-fancy-bear.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,408 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: 2 findings, up to high

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 →

  • high YARA Match · line 75
    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 95
    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.
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 $0.00050 $0.06408
Opus 5 $0.00025 $0.03204
Sonnet 5 $0.00010 $0.01282
Haiku 4.5 $0.00005 $0.00641

Measured 11d ago against content hash 96e4ee04ccff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

apt28-fancy-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/apt28-fancy-bear/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APT28 (Fancy Bear, Forest Blizzard, Sofacy, STRONTIUM) — Adversary Emulation Profile

APT28 (MITRE ATT&CK G0007) is a long-running cyber-espionage group attributed to Russia's General Staff Main Intelligence Directorate (GRU) 85th Main Special Service Center (GTsSS), military unit 26165, operating since at least 2004. Across two decades it has hit governments, militaries, diplomatic bodies, defense and aerospace, anti-doping and chemical-weapons watchdogs, media, and — since 2022 — Western logistics and IT firms supporting Ukraine. APT28 is best characterized by disciplined credential operations (spearphishing, large-scale password spraying, NTLM-coercion), pragmatic use of N-day exploits (Outlook, Exchange, WinRAR, Windows Print Spooler), a broad cross-platform malware stable (Windows/Linux/macOS/Android, plus the LoJax UEFI rootkit), and a willingness to pivot from pure espionage into influence, hack-and-leak, and occasional destructive/DDoS operations. This profile maps its tradecraft to ATT&CK so Decepticon can emulate it inside an authorized engagement and the blue cell can anticipate detection.

Attribution & motivation

  • Sponsor / nation: Russian Federation — GRU 85th GTsSS, Military Unit 26165. The 2018 U.S. DOJ indictments named specific GRU officers of Units 26165 and 74455; the UK, EU, and France have formally attributed multiple campaigns to this unit.
  • Motivation: Primarily strategic intelligence collection (espionage) aligned with Russian state interests — military, diplomatic, and political intelligence. Secondary motivations include influence / information operations (hack-and-leak against the 2016 U.S. election, WADA athlete data dumps) and occasional destructive / disruptive action (TV5Monde disruption, WADA DDoS).
  • Attribution confidence: High. Backed by U.S. DOJ criminal indictments and coordinated government attributions (UK NCSC, EU, France ANSSI/MFA) plus consistent named vendor reporting (Microsoft, Mandiant, Palo Alto Unit 42, ESET).

Read the full file on GitHub · 218 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 · 218 lines · 50 tokens per session scan A 96e4ee04ccff

Subscribe to this mod's changes

apt28-fancy-bear is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 50 tokens to every session and 6,408 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.