sandworm-team

sandworm-team is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 55 tokens per session (5,522 once invoked), scanned A, original, Apache-2.0.

A profile of Sandworm Team, a Russian military-linked cyber group known for destructive attacks and influence operations, including attacks on industrial control systems such as power grids.

In plain words
What is it for?
Use it to study Sandworm's background, targets, tools, and attack methods when planning threat analysis or authorised adversary-emulation exercises.
Why use it?
It gives security teams a reference for recognising and safely modelling this group's reported behaviour during authorised testing.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to study Sandworm's background, targets, tools, and attack methods when planning threat analysis or authorised adversary-emulation exercises.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/sandworm-team
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 · 5,471 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 sandworm-team
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 sandworm-team

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/sandworm-team"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/sandworm-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,522 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: 4 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 60
    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.
  • high YARA Match · line 68
    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.
  • medium Rogue Agent · line 64
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00055 $0.05522
Opus 5 $0.00028 $0.02761
Sonnet 5 $0.00011 $0.01104
Haiku 4.5 $0.00006 $0.00552

Measured 10d ago against content hash f540a6c78231, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sandworm-team 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 10d 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/sandworm-team/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sandworm Team (Voodoo Bear, Seashell Blizzard, ELECTRUM) — Adversary Emulation Profile

Sandworm Team (MITRE ATT&CK G0034; also tracked as APT44, Voodoo Bear, Seashell Blizzard, ELECTRUM, Telebots, IRON VIKING, IRIDIUM, FROZENBARENTS, and historically BlackEnergy/Quedagh) is a destructive Russian state threat group attributed to the GRU's Main Center for Special Technologies (GTsST), military unit 74455, active since at least 2009. Unlike espionage-focused peers, Sandworm is the GRU's premier sabotage and influence unit: it pairs conventional intrusion tradecraft with bespoke ICS/OT attack capability, disk wipers, fake ransomware, hacktivist-persona leaks, and disruptive operations timed to geopolitical and kinetic events. It is the only actor publicly documented to have triggered electric-grid blackouts via cyberattack (Ukraine, 2015 and 2016) and later repeated an OT grid attack in 2022. This profile maps Sandworm's signature TTPs to ATT&CK so Decepticon can emulate them within an authorized engagement and so the blue cell can anticipate detection.

Attribution & motivation

  • Sponsor / nation: Russian Federation — GRU (Main Intelligence Directorate), Main Center for Special Technologies (GTsST), military unit 74455. Attribution is high confidence, backed by the October 2020 US DOJ indictment of six named Unit 74455 officers, concurrent UK/EU/Five Eyes statements, and Mandiant's April 2024 graduation of the cluster to the named APT designation APT44.
  • Motivation: Primarily destructive/disruptive sabotage and influence operations in support of Russian military and political objectives, with espionage and pre-positioning for access as enabling activity. Financial theft is rare and generally a cover (e.g., NotPetya and Prestige used ransomware/wiper framing for destructive ends rather than profit).
  • Strategic character: Operations are frequently synchronized with kinetic events (e.g., the October 2022 OT attack coincided with Russian missile strikes on Ukraine) and elections, and use false hacktivist or criminal personas for plausible deniability.

Read the full file on GitHub · 143 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. 10d ago First seen · 143 lines · 55 tokens per session scan A f540a6c78231

Subscribe to this mod's changes

sandworm-team is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 55 tokens to every session and 5,522 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.