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 apt28-fancy-beargit 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/apt28-fancy-bear)<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt28-fancy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt28-fancy-bear/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/apt28-fancy-bear"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt28-fancy-bear.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 75 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 95 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 | $0.00050 | $0.06408 |
| Opus 5 | $0.00025 | $0.03204 |
| Sonnet 5 | $0.00010 | $0.01282 |
| Haiku 4.5 | $0.00005 | $0.00641 |
Grade A, and why
apt28-fancy-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 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.
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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APT28 (Fancy Bear, Forest Blizzard, Sofacy, STRONTIUM) — Adversary Emulation Profile
APT28 (MITRE ATT&CK G0007) is a long-running cyber-espionage group attributed to Russia's General Staff Main Intelligence Directorate (GRU) 85th Main Special Service Center (GTsSS), military unit 26165, operating since at least 2004. Across two decades it has hit governments, militaries, diplomatic bodies, defense and aerospace, anti-doping and chemical-weapons watchdogs, media, and — since 2022 — Western logistics and IT firms supporting Ukraine. APT28 is best characterized by disciplined credential operations (spearphishing, large-scale password spraying, NTLM-coercion), pragmatic use of N-day exploits (Outlook, Exchange, WinRAR, Windows Print Spooler), a broad cross-platform malware stable (Windows/Linux/macOS/Android, plus the LoJax UEFI rootkit), and a willingness to pivot from pure espionage into influence, hack-and-leak, and occasional destructive/DDoS operations. This profile maps its tradecraft to ATT&CK so Decepticon can emulate it inside an authorized engagement and the blue cell can anticipate detection.
Attribution & motivation
- Sponsor / nation: Russian Federation — GRU 85th GTsSS, Military Unit 26165. The 2018 U.S. DOJ indictments named specific GRU officers of Units 26165 and 74455; the UK, EU, and France have formally attributed multiple campaigns to this unit.
- Motivation: Primarily strategic intelligence collection (espionage) aligned with Russian state interests — military, diplomatic, and political intelligence. Secondary motivations include influence / information operations (hack-and-leak against the 2016 U.S. election, WADA athlete data dumps) and occasional destructive / disruptive action (TV5Monde disruption, WADA DDoS).
- Attribution confidence: High. Backed by U.S. DOJ criminal indictments and coordinated government attributions (UK NCSC, EU, France ANSSI/MFA) plus consistent named vendor reporting (Microsoft, Mandiant, Palo Alto Unit 42, ESET).
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 · 218 lines · 50 tokens per session scan A 96e4ee04ccff
apt28-fancy-bear is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 50 tokens to every session and 6,408 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.
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.
implementing-zero-trust-with-beyondcorp
Use when deploy Google BeyondCorp Enterprise zero trust access controls using Identity-Aware Proxy (IAP), context-aware access policies, device trust validation, and Access Context Manager to enforce identity and posture-based access to GCP resources and internal applications. Use when deploying google beyondcorp…