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 apt37-reapergit 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/apt37-reaper)<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt37-reaper"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt37-reaper/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/apt37-reaper"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt37-reaper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 153 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 155 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.
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 | $0.00053 | $0.06117 |
| Opus 5 | $0.00026 | $0.03059 |
| Sonnet 5 | $0.00011 | $0.01223 |
| Haiku 4.5 | $0.00005 | $0.00612 |
Grade A, and why
apt37-reaper 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APT37 (Reaper, ScarCruft, Ricochet Chollima, InkySquid) — Adversary Emulation Profile
APT37 (MITRE ATT&CK G0067) is a North Korean state-sponsored cyber-espionage group active since at least 2012. Tracked as ScarCruft (Kaspersky), Reaper (FireEye), InkySquid (Volexity), Group123 (Cisco Talos), TEMP.Reaper, and Ricochet Chollima (CrowdStrike), APT37 primarily targets South Korean government, military, media, and defector communities, with expanding operations into Japan, Vietnam, the Middle East, and Europe. The group is characterized by aggressive exploitation of zero-day vulnerabilities in Adobe Flash Player, Internet Explorer, and Microsoft Edge; heavy use of weaponized Hangul Word Processor (HWP) documents; strategic web compromises (watering holes); a diverse custom malware arsenal (RoKRAT, BLUELIGHT, Chinotto, Dolphin, DOGCALL); and C2 over legitimate cloud services (Dropbox, pCloud, Yandex, Box, Google Drive). Unlike the higher-profile Lazarus Group, APT37 focuses on targeted intelligence collection and defector surveillance rather than financial theft or destructive operations.
Attribution & motivation
- Sponsor / nation: Democratic People's Republic of Korea (North Korea) — Reconnaissance General Bureau (RGB). FireEye's 2018 report assessed APT37 as a North Korean state-sponsored group with "high confidence," based on malware compilation timestamps aligned with Pyongyang working hours (UTC+8:30/+9), Korean-language resources in binaries, targeting patterns consistent with DPRK state interests, and overlapping infrastructure with other attributed DPRK operations.
- Motivation: Primarily strategic intelligence collection (espionage) — surveillance of North Korean defectors, journalists covering DPRK affairs, and human-rights activists; collection of South Korean military, government, and diplomatic intelligence. Secondary missions include pre-positioning for destructive operations (MBR-wiping malware capability) and technology/defense intelligence collection from aerospace, chemicals, electronics, and manufacturing sectors.
- Attribution confidence: High. FireEye's 2018 "APT37: The Overlooked North Korean Actor" report, Kaspersky's ScarCruft tracking (Operation Daybreak, Bluetooth harvester), Cisco Talos "Korea in the Crosshairs," Volexity's InkySquid browser-exploit research, and consistent multi-vendor reporting over a decade.
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 · 189 lines · 53 tokens per session scan A 7793b9a233ac
apt37-reaper is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 53 tokens to every session and 6,117 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.