scattered-spider

scattered-spider is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 49 tokens per session (5,548 once invoked), scanned A, original, Apache-2.0.

An adversary-emulation profile for Scattered Spider, a financially motivated cybercriminal group known for social engineering, identity attacks, cloud compromise, data theft, and ransomware operations.

In plain words
What is it for?
Use it to plan or assess exercises involving help-desk impersonation, MFA abuse, cloud identity access, VMware environments, data staging, and ransomware-related behavior.
Why use it?
It gives security teams a documented model of this group’s tactics and tools for authorized defensive exercises. It focuses on identity and help-desk processes as well as later cloud and virtualization activity.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan or assess exercises involving help-desk impersonation, MFA abuse, cloud identity access, VMware environments, data staging, and ransomware-related behavior.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/scattered-spider
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 scattered-spider
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 scattered-spider

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/scattered-spider"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/scattered-spider.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,548 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 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 3
    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 44
    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 71
    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 82
    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 131
    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 $0.00049 $0.05548
Opus 5 $0.00024 $0.02774
Sonnet 5 $0.00010 $0.01110
Haiku 4.5 $0.00005 $0.00555

Measured 10d ago against content hash a6b557e4699d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

scattered-spider 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/scattered-spider/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scattered Spider (UNC3944, Octo Tempest, Muddled Libra, Star Fraud) — Adversary Emulation Profile

Scattered Spider (MITRE ATT&CK G1015) is a financially motivated, predominantly native English-speaking cybercriminal collective active since at least 2022 and widely linked to the loosely affiliated "The Com" social network. The group is exceptional not for novel malware but for aggressive, high-tempo social engineering of human identity processes: it phones and SMS-phishes help desks and employees, impersonates IT staff, bypasses MFA (push bombing, SIM swapping, attacker-registered tokens), and rapidly pivots into cloud identity (Microsoft Entra ID, Okta, AWS, Azure) and virtualization (VMware ESXi/vCenter) before staging data theft and ransomware. It began with the 2022 "0ktapus" Okta-credential phishing wave, escalated to the high-profile 2023 MGM Resorts and Caesars Entertainment intrusions, and through 2024–2025 operated as an affiliate of multiple ransomware-as-a-service brands (BlackCat/ALPHV, RansomHub, Qilin, DragonForce), hitting retail, insurance, and aviation. This profile teaches Decepticon to emulate G1015's signature identity-centric TTPs inside an authorized engagement and helps the blue cell anticipate detection.

Attribution & motivation

  • Sponsor / nation: Non-state, criminal. Members are assessed to be primarily young, native English speakers based in the US and UK, affiliated with the broader "The Com" cybercrime community. Not a nation-state actor; multiple arrests and a 2025 US extradition have been reported (per Krebs on Security / Infosecurity Magazine).
  • Motivation: Primarily financial — credential theft, SIM-swap fraud / crypto theft, data extortion, and ransomware (T1657 Financial Theft). There is no credible espionage, destructive-only, or influence mandate; destruction (encryption) is in service of extortion.
  • Confidence: High confidence the cluster tracked as Scattered Spider = UNC3944 (Mandiant/Google) = Octo Tempest / Storm-0875 (Microsoft) = Muddled Libra (Palo Alto Unit 42) = Roasted 0ktapus = Scatter Swine = Star Fraud. Note these vendor clusters overlap but are not byte-for-byte identical; treat as a fluid affiliate community rather than a fixed roster.

Read the full file on GitHub · 171 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 · 171 lines · 49 tokens per session scan A a6b557e4699d

Subscribe to this mod's changes

scattered-spider is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 49 tokens to every session and 5,548 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 2026-08-30.