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 kimsukygit 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/kimsuky)<a href="https://agentmods.dev/skills/purpleailab/decepticon/kimsuky"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/kimsuky/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/kimsuky"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/kimsuky.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 Prompt Injection · line 3 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
- critical Prompt Injection · line 7 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
- critical Prompt Injection · line 12 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
- critical Prompt Injection · line 8 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
- high YARA Match · line 26 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 52 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 72 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 216 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.
- medium Rogue Agent · line 80 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.
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 | $0.00066 | $0.08298 |
| Opus 5 | $0.00033 | $0.04149 |
| Sonnet 5 | $0.00013 | $0.01660 |
| Haiku 4.5 | $0.00007 | $0.00830 |
Grade A, and why
kimsuky-velvet-chollima 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kimsuky (Velvet Chollima, Emerald Sleet, THALLIUM, Black Banshee, APT43) — Adversary Emulation Profile
Kimsuky (MITRE ATT&CK G0094) is a DPRK-based cyber-espionage group attributed to North Korea's Reconnaissance General Bureau (RGB), specifically the 63rd Research Center, operating since at least 2012. Initially focused on South Korean government entities and think tanks, the group has expanded its aperture to the United States, Japan, Russia, and Europe — consistently targeting individuals and organizations with insight into Korean Peninsula foreign policy, nuclear policy, sanctions, and defense issues. Kimsuky is distinguished by its heavy investment in social engineering and credential phishing over zero-day exploitation: the group impersonates journalists, researchers, diplomats, and think-tank personnel in long-running correspondence campaigns to build trust before delivering malicious payloads or harvesting credentials. Its tooling ranges from commodity RATs (QuasarRAT, gh0st RAT) to a stable of bespoke malware families (BabyShark, AppleSeed, Gold Dragon, KONNI, Troll Stealer) and malicious browser extensions (TRANSLATEXT). Since 2023, Kimsuky has been observed leveraging commercial LLMs for target research and vulnerability analysis, and adopting ClickFix-style social engineering to trick victims into self-executing malicious PowerShell.
Attribution & motivation
- Sponsor / nation: Democratic People's Republic of Korea (DPRK) — Reconnaissance General Bureau (RGB), 63rd Research Center. U.S. government (CISA/FBI/CNMF joint advisory AA20-301A, 2020) and multiple vendor assessments (Mandiant/Google TAG, CrowdStrike, Microsoft, Symantec) attribute Kimsuky operations to North Korean state-sponsored actors. In 2023, the U.S. Treasury sanctioned Kimsuky as an entity of the RGB.
- Motivation: Primarily strategic intelligence collection (espionage) — gathering foreign policy, nuclear/defense, and sanctions intelligence for the DPRK regime. Secondary motivation includes financial theft (cryptocurrency theft and laundering to self-fund operations, per Mandiant's APT43 report) and limited influence operations (DMARC abuse for impersonation campaigns).
- Attribution confidence: High. Supported by U.S. government joint advisories (AA20-301A), FBI IC3 public service announcements (2026), Treasury OFAC sanctions designations, and consistent multi-vendor reporting (Mandiant, CrowdStrike, Microsoft, Symantec, Kaspersky, Malwarebytes, Cisco Talos, Proofpoint, Zscaler).
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 · 250 lines · 66 tokens per session scan A a7950eb87b17
kimsuky-velvet-chollima is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 66 tokens to every session and 8,298 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.