apt10-stone-panda

apt10-stone-panda is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 52 tokens per session (6,788 once invoked), scanned A, original, Apache-2.0.

A profile of APT10, also called Stone Panda or menuPass, a Chinese cyber-espionage group tracked by the MITRE ATT&CK system. It describes the group's history, targets, tools, and attack methods, including attacks through managed IT providers.

In plain words
What is it for?
Use it to study APT10 behavior, prepare adversary-emulation exercises, and understand relevant malware, public tools, targets, and supply-chain attack patterns.
Why use it?
It gives security teams a consistent description of a known threat actor and the techniques associated with it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to study APT10 behavior, prepare adversary-emulation exercises, and understand relevant malware, public tools, targets, and supply-chain attack patterns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/apt10-stone-panda
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 apt10-stone-panda
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 apt10-stone-panda

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/apt10-stone-panda/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/apt10-stone-panda)
Your own site
<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.

agentmods 80×15 button for apt10-stone-panda

Your own site · 80×15
<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>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,788 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: 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.
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 $0.00052 $0.06788
Opus 5 $0.00026 $0.03394
Sonnet 5 $0.00010 $0.01358
Haiku 4.5 $0.00005 $0.00679

Measured 10d ago against content hash af0fef11f16a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

packages/decepticon/decepticon/skills/shared/adversary-emulation/apt10-stone-panda/SKILL.md · 209 lines

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).

Read the full file on GitHub · 209 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 · 209 lines · 52 tokens per session scan A af0fef11f16a

Subscribe to this mod's changes

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.