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 apt10-stone-pandagit 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/apt10-stone-panda)<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt10-stone-panda"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt10-stone-panda/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/apt10-stone-panda"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt10-stone-panda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 14 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 153 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 | $0.00052 | $0.06788 |
| Opus 5 | $0.00026 | $0.03394 |
| Sonnet 5 | $0.00010 | $0.01358 |
| Haiku 4.5 | $0.00005 | $0.00679 |
Grade A, and why
apt10-stone-panda 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APT10 (Stone Panda, menuPass, POTASSIUM, Red Apollo) — Adversary Emulation Profile
APT10 (MITRE ATT&CK G0045) is a long-running Chinese cyber-espionage group active since at least 2006, attributed to China's Ministry of State Security (MSS) Tianjin State Security Bureau. Individual members have been identified as working for the Huaying Haitai Science and Technology Development Company. APT10 is best known for Operation Cloud Hopper — the systematic, large-scale compromise of managed IT service providers (MSPs) to pivot into hundreds of downstream client organizations worldwide — a paradigm-defining supply-chain attack. The group's toolkit spans custom implants (PlugX, RedLeaves, ChChes, UPPERCUT/ANEL, SodaMaster, Ecipekac), public frameworks (QuasarRAT, Cobalt Strike, Mimikatz, PsExec), and heavy reliance on DLL side-loading for evasion. Targeting is broad: healthcare, defense, aerospace, government, telecom, maritime, finance, and biotechnology, with a persistent emphasis on Japanese organizations and Western MSPs.
Attribution & motivation
- Sponsor / nation: People's Republic of China — Ministry of State Security (MSS), Tianjin State Security Bureau. The December 2018 U.S. DOJ indictment named two MSS-linked operatives, Zhu Hua (朱华) and Zhang Shilong (张士龙), as APT10 members employed by Huaying Haitai Science and Technology Development Company. Joint attributions by the UK (NCSC), Japan, Australia, Canada, and the EU corroborated the MSS link.
- Motivation: Primarily economic espionage and intellectual-property theft aligned with Chinese state industrial policy — stealing trade secrets, engineering data, and business-confidential information from technology, aerospace, defense, pharmaceutical, and energy sectors. Secondary motivation includes strategic intelligence collection (government, diplomatic, and telecom surveillance — e.g., Call Detail Records in Operation Soft Cell).
- Attribution confidence: High. Backed by U.S. DOJ criminal indictments (SDNY, Dec 2018), coordinated Five Eyes + EU government attributions, and consistent named vendor reporting (FireEye/Mandiant, PwC/BAE Systems, Symantec, Kaspersky, Palo Alto Unit 42, Cybereason, Accenture).
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 · 209 lines · 52 tokens per session scan A af0fef11f16a
apt10-stone-panda is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 52 tokens to every session and 6,788 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.