volt-typhoon

volt-typhoon is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 42 tokens per session (5,055 once invoked), scanned A, original, Apache-2.0.

A cybersecurity profile describing Volt Typhoon, a China-linked state-sponsored group tracked by MITRE ATT&CK as G1017.

In plain words
What is it for?
Use it to plan adversary-emulation exercises and compare observed activity in critical infrastructure environments with Volt Typhoon’s documented tactics.
Why use it?
It gives defenders a reference for the group’s known behaviour, including quiet access, stolen credentials, and use of legitimate system tools.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to plan adversary-emulation exercises and compare observed activity in critical infrastructure environments with Volt Typhoon’s documented tactics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/volt-typhoon
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 · 5,452 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 volt-typhoon
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 volt-typhoon

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/volt-typhoon.svg)](https://agentmods.dev/skills/purpleailab/decepticon/volt-typhoon)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/volt-typhoon"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/volt-typhoon.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,055 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: 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 73
    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.
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 $0.00042 $0.05055
Opus 5 $0.00021 $0.02527
Sonnet 5 $0.00008 $0.01011
Haiku 4.5 $0.00004 $0.00505

Measured 8d ago against content hash f2d4a64212c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

volt-typhoon 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 8d 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/volt-typhoon/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Volt Typhoon (BRONZE SILHOUETTE, Vanguard Panda, Insidious Taurus) — Adversary Emulation Profile

Volt Typhoon is a People's Republic of China (PRC) state-sponsored cyber actor active since at least mid-2021, tracked by MITRE ATT&CK as G1017 and known by the aliases BRONZE SILHOUETTE (Secureworks), Vanguard Panda (CrowdStrike), Voltzite (Dragos), Insidious Taurus (Palo Alto Unit 42), DEV-0391 (Microsoft's pre-naming designation), and UNC3236 (Mandiant). Unlike financially motivated crews, Volt Typhoon's hallmark is patient, ultra-stealthy pre-positioning inside US critical infrastructure — communications, energy, water, and transportation — using almost exclusively living-off-the-land (LOTL) techniques and legitimate stolen credentials, with little or no custom malware on victim hosts. CISA, the NSA, and the FBI assess the group is establishing persistent access not for immediate espionage value but to enable lateral movement to operational technology (OT) for potential disruptive or destructive attacks during a future geopolitical crisis or conflict. Its operational signature is hands-on-keyboard activity, native OS binaries, web shells on edge appliances, and traffic proxied through compromised small-office/home-office (SOHO) routers to blend into normal network noise.

Attribution & motivation

  • Sponsor / nation: People's Republic of China (PRC), state-sponsored. CISA/NSA/FBI and Microsoft attribute the activity to a PRC nexus; Microsoft assessed the actor as PRC state-sponsored with high confidence.
  • Motivation: Strategic pre-positioning / preparation of the environment rather than classic data-theft espionage. Microsoft assessed with moderate confidence that the campaign pursues capabilities that could disrupt critical communications infrastructure between the US and the Asia region during a future crisis. CISA's AA24-038A frames the intent as enabling destructive or disruptive cyberattacks against OT in the event of conflict. This is closer to destructive/wartime-enabling than financial or influence motivation.
  • Confidence: Attribution to a PRC state-sponsored actor is high (joint government + multiple vendor concurrence). The disruptive-intent assessment is moderate confidence per the original reporting.

Read the full file on GitHub · 162 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. 8d ago First seen · 162 lines · 42 tokens per session scan A f2d4a64212c8

Subscribe to this mod's changes

volt-typhoon is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,452 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 5,055 once invoked, about $0.0002 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.