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.
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.
npx skills add PurpleAILAB/Decepticon --skill lazarus-groupgit clone --depth 1 https://github.com/PurpleAILAB/DecepticonWrote 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.
[](https://agentmods.dev/skills/purpleailab/decepticon/lazarus-group)<a href="https://agentmods.dev/skills/purpleailab/decepticon/lazarus-group"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/lazarus-group/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.
<a href="https://agentmods.dev/skills/purpleailab/decepticon/lazarus-group"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/lazarus-group.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 117 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.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.05270 |
| Opus 5 | $0.00026 | $0.02635 |
| Sonnet 5 | $0.00010 | $0.01054 |
| Haiku 4.5 | $0.00005 | $0.00527 |
Grade A, and why
lazarus-group 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lazarus Group (Hidden Cobra, Diamond Sleet, Labyrinth Chollima) — Adversary Emulation Profile
Lazarus Group (MITRE ATT&CK G0032) is a North Korean state-sponsored threat actor active since at least 2009 and attributed by the U.S. Government and the security industry to the DPRK's Reconnaissance General Bureau (RGB). It is one of the most versatile and prolific nation-state actors observed, running three overlapping mission types in parallel: strategic espionage, destructive/disruptive attacks (e.g., the 2014 Sony Pictures wiper and the 2017 WannaCry outbreak), and large-scale financially motivated theft to fund the sanctioned regime (SWIFT bank fraud, ATM "FASTCash" cash-outs, and cryptocurrency heists). MITRE and vendors track several clusters/aliases under or alongside the Lazarus umbrella — HIDDEN COBRA, Guardians of Peace, ZINC, NICKEL ACADEMY, Diamond Sleet (Microsoft), and Labyrinth Chollima (CrowdStrike) — with financial sub-clusters often labeled APT38 / BlueNoroff / Stardust Chollima. The group blends bespoke malware, trojanized legitimate software, supply-chain compromise, and elaborate social engineering (fake recruiter "job offers") to reach hardened targets.
Attribution & motivation
- Suspected sponsor / nation: North Korea (DPRK), tied to the Reconnaissance General Bureau (RGB). The U.S. Government uses the umbrella name HIDDEN COBRA for DPRK malicious cyber activity.
- Motivation (mixed):
- Financial — sanctions-driven revenue generation: SWIFT interbank fraud, FASTCash ATM cash-outs, and cryptocurrency theft from exchanges, DeFi, and blockchain firms.
- Espionage — collection against defense, aerospace, government, and crypto/fintech targets, frequently via fake-job-offer lures (Operation Dream Job).
- Destructive / disruptive — wiper and ransomware operations (Sony Pictures 2014; WannaCry 2017).
- Confidence of attribution: High. Backed by a 2018 U.S. DOJ criminal complaint naming DPRK programmer Park Jin Hyok, multiple joint FBI/CISA/Treasury/USCYBERCOM advisories, and corroborating Mandiant/ESET/Kaspersky/Microsoft reporting. Individual sub-cluster boundaries (Lazarus vs. APT38/BlueNoroff) carry moderate analyst-to-analyst variance.
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.
- 10d ago First seen · 146 lines · 51 tokens per session scan A 0ada8241ddd3
lazarus-group is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 51 tokens to every session and 5,270 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.
Other skills, from other repositories
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
onboarding
First-time user onboarding to set up investment profile, watchlists, portfolio, and preferences.
idea-generation
Stock screening and idea generation: quantitative screens, thematic analysis, shortlist.
secretary
Workspace and research management — dispatch analyses, monitor running agents, manage workspaces and threads.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
analyzing-windows-prefetch-with-python
Use when parse Windows Prefetch files using the windowsprefetch Python library to reconstruct application execution history, detect renamed or masquerading binaries, and identify suspicious program execution patterns. Use when working with analyzing windows prefetch with python.