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 mustang-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/mustang-panda)<a href="https://agentmods.dev/skills/purpleailab/decepticon/mustang-panda"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mustang-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/mustang-panda"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/mustang-panda.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 41 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
- critical 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.
- high YARA Match · line 41 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.
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 | $0.00058 | $0.08551 |
| Opus 5 | $0.00029 | $0.04276 |
| Sonnet 5 | $0.00012 | $0.01710 |
| Haiku 4.5 | $0.00006 | $0.00855 |
Grade C, and why
mustang-panda-bronze-president scanned grade C with 2 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 11d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **T1003** — OS credential dumping. Used "Hdump" to dump credentials from memory. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **T1567.002** — Exfiltration to cloud storage. Exfiltrated archived files to Dropbox using `curl`. How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mustang Panda (Bronze President, Stately Taurus, RedDelta, TA416) — Adversary Emulation Profile
Mustang Panda (MITRE ATT&CK G0129) is a China-based cyber-espionage threat actor conducting operations since at least 2012. Tracked under a dozen aliases — Bronze President (Secureworks), Stately Taurus / FIREANT (Unit 42), RedDelta (Recorded Future), TA416 (Proofpoint), Earth Preta (Trend Micro), HIVE0154 (IBM X-Force), Camaro Dragon (Check Point), Twill Typhoon / TANTALUM (Microsoft), LUMINOUS MOTH, UNC6384 / TEMP.Hex (Mandiant/Google TAG), Red Lich (PwC), and ClumsyToad (Cloudflare) — the group is best known for its prolific use of PlugX/Korplug RAT variants delivered through DLL side-loading, themed spearphishing lures, and USB-based propagation. Mustang Panda targets government, diplomatic, military, NGO, think-tank, and religious entities across Southeast Asia, Europe, and beyond, with sustained focus on Myanmar, Vietnam, the Philippines, Cambodia, Taiwan, Japan, Mongolia, and — since 2022 — European diplomatic bodies and Russia-related targets.
Attribution & motivation
- Sponsor / nation: People's Republic of China — assessed as a state-sponsored espionage actor with a Chinese nexus. CrowdStrike first attributed the group in 2017; subsequent reporting from Secureworks, Recorded Future, Proofpoint, Trend Micro, Unit 42, Check Point, IBM X-Force, and Google TAG consistently attribute operations to PRC interests. A December 2024 U.S. DOJ affidavit supported seizure of U.S.-based computers infected with Mustang Panda's PlugX malware, formally linking the tool to PRC state-sponsored activity.
- Motivation: Primarily strategic intelligence collection (espionage) aligned with PRC foreign-policy interests — diplomatic, military, and political intelligence from Southeast Asian governments, European diplomatic bodies, and organizations involved in issues sensitive to Beijing (Tibet, Taiwan, South China Sea, religious organizations).
- Attribution confidence: High. Backed by consistent multi-vendor reporting (CrowdStrike, Secureworks, Recorded Future, Proofpoint, Unit 42, Trend Micro, ESET, Check Point, IBM X-Force, Google TAG, Zscaler), U.S. DOJ law-enforcement action (2024 PlugX seizure warrant), and shared infrastructure/tooling overlap across campaigns spanning 10+ years.
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.
- 11d ago First seen · 258 lines · 58 tokens per session scan C a4a2ee634815
mustang-panda-bronze-president is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 58 tokens to every session and 8,551 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). 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.