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 muddywatergit 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/muddywater)<a href="https://agentmods.dev/skills/purpleailab/decepticon/muddywater"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/muddywater/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/muddywater"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/muddywater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 32 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 89 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.
- high YARA Match · line 121 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 | $0.00053 | $0.09002 |
| Opus 5 | $0.00026 | $0.04501 |
| Sonnet 5 | $0.00011 | $0.01800 |
| Haiku 4.5 | $0.00005 | $0.00900 |
Grade C, and why
muddywater-mango-sandstorm scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **T1555** — Credentials from Password Stores: LaZagne and other tools dump credentials from email clients and password stores. How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MuddyWater (Mercury, Mango Sandstorm, Static Kitten, Seedworm, TEMP.Zagros) — Adversary Emulation Profile
MuddyWater (MITRE ATT&CK G0069) is a cyber-espionage group assessed to be a subordinate element within Iran's Ministry of Intelligence and Security (MOIS), active since at least 2017. The group has targeted government, telecommunications, defense, oil & gas, and IT organizations across the Middle East, Central/South Asia, Africa, Europe, and North America. MuddyWater is characterized by heavy reliance on PowerShell-based backdoors (POWERSTATS and its successors), evolving custom C2 frameworks (PhonyC2 → MuddyC2Go), abuse of legitimate Remote Monitoring and Management (RMM) tools (Atera, ScreenConnect, SimpleHelp), spearphishing with macro-laden documents, and a pragmatic blend of custom and open-source post-exploitation tooling. A February 2022 joint U.S./UK advisory (CISA AA22-055A) formally attributed the group to MOIS.
Attribution & motivation
- Sponsor / nation: Islamic Republic of Iran — Ministry of Intelligence and Security (MOIS). U.S. Cyber Command's Cyber National Mission Force (CNMF) publicly linked MuddyWater to MOIS in January 2022; the February 2022 joint FBI/CISA/CNMF/NCSC-UK advisory AA22-055A formalized the attribution.
- Motivation: Primarily strategic intelligence collection (espionage) supporting Iranian state interests — political, military, and economic intelligence on regional rivals. Secondary motivations include pre-positioning for disruptive operations (the 2023 Technion "DarkBit" ransomware incident) and access brokerage (sharing/selling network access to other MOIS-aligned threat actors).
- Attribution confidence: High. Backed by U.S. government advisories (CISA AA22-055A), UK NCSC malware analysis reports, Israel National Cyber Directorate attributions, and consistent named vendor reporting (Microsoft, ESET, Deep Instinct, Cisco Talos, Symantec, ClearSky, Trend Micro, Proofpoint, Group-IB).
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 · 281 lines · 53 tokens per session scan C fb709a2e608e
muddywater-mango-sandstorm is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 53 tokens to every session and 9,002 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). 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.