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 turlagit 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/turla)<a href="https://agentmods.dev/skills/purpleailab/decepticon/turla"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/turla/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/turla"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/turla.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 49 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 49 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 85 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.
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 | $0.00055 | $0.10222 |
| Opus 5 | $0.00028 | $0.05111 |
| Sonnet 5 | $0.00011 | $0.02044 |
| Haiku 4.5 | $0.00006 | $0.01022 |
Grade A, and why
turla-venomous-bear 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 9d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turla (Venomous Bear, Secret Blizzard, Waterbug, KRYPTON, Snake) — Adversary Emulation Profile
Turla (MITRE ATT&CK G0010) is one of the most sophisticated and long-running cyber-espionage groups in existence, attributed to Russia's Federal Security Service (FSB) Center 16, operating since at least 2004. Turla has compromised victims in over 50 countries across government, diplomatic, military, defense, education, research, and pharmaceutical sectors. The group is characterized by extraordinary technical depth — from the Snake/Uroburos kernel rootkit and satellite-based C2 hijacking to steganographic email backdoors and the audacious practice of hijacking other nation-state APTs' infrastructure. Turla's tooling spans Windows, Linux, and macOS, with a malware ecosystem (Snake, Carbon, ComRAT, Kazuar, LightNeuron, Penquin, TinyTurla, Lunar toolset) unmatched in breadth and longevity. The 2023 FBI Operation MEDUSA takedown of the Snake peer-to-peer network — spanning 50+ countries over nearly 20 years — underscored the global scale of Turla's operations.
Attribution & motivation
- Sponsor / nation: Russian Federation — Federal Security Service (FSB), Center 16. CISA has formally attributed Turla / Secret Blizzard to FSB Center 16. The 2023 joint FBI/CISA/NSA advisory (AA23-129A) detailed the Snake malware infrastructure and attributed it to FSB officers. The NSA/NCSC 2019 joint advisory documented Turla's hijacking of Iranian APT infrastructure and attributed it to the same FSB unit.
- Motivation: Primarily strategic intelligence collection (espionage) — diplomatic, military, political, and scientific intelligence aligned with Russian state interests. Turla is a pure espionage actor with no documented financially motivated or destructive campaigns; its sole objective is persistent, covert access to high-value targets for long-term intelligence gathering.
- Attribution confidence: High. Backed by U.S. DOJ court filings (Operation MEDUSA), joint CISA/NSA/FBI advisories, NSA/NCSC joint attributions, and consistent named vendor reporting (ESET, Kaspersky, Microsoft, Symantec/Broadcom, Palo Alto Unit 42, Mandiant, Cisco Talos, 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.
- 9d ago First seen · 275 lines · 55 tokens per session scan A b5080bab7401
turla-venomous-bear is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,463 stars, last pushed 9d ago), licensed Apache-2.0. It adds 55 tokens to every session and 10,222 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.