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 fin7-carbanakgit 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/fin7-carbanak)<a href="https://agentmods.dev/skills/purpleailab/decepticon/fin7-carbanak"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/fin7-carbanak/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/fin7-carbanak"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/fin7-carbanak.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 81 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 96 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.
- high YARA Match · line 134 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 | $0.00068 | $0.05942 |
| Opus 5 | $0.00034 | $0.02971 |
| Sonnet 5 | $0.00014 | $0.01188 |
| Haiku 4.5 | $0.00007 | $0.00594 |
Grade B, and why
fin7-carbanak scanned grade B 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 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 variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **T1003 — OS Credential Dumping:** Uses Mimikatz (S0002) to harvest credentials. *(ATT&CK software mapping; mapped to T1003)* Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FIN7 (Carbanak, Carbon Spider, Sangria Tempest) — Adversary Emulation Profile
FIN7 (MITRE ATT&CK G0046; also tracked as Carbanak, Carbon Spider, Sangria Tempest, GOLD NIAGARA, ELBRUS, and ITG14) is one of the most prolific and best-documented financially motivated cybercrime groups, active since at least 2013. Originally infamous for large-scale point-of-sale (POS) intrusions to steal payment-card data — operating behind the front company "Combi Security" — the group pivoted to "big game hunting" ransomware around 2020, running its own Darkside/BlackMatter Ransomware-as-a-Service and acting as an affiliate/tooling supplier for REvil, Cl0p, Black Basta, ALPHV/BlackCat, LockBit, and others. FIN7 is characterized by disciplined operational tradecraft: convincing social engineering (including spearphishing of IT staff and physically mailed BadUSB drives), heavily obfuscated custom loaders (POWERTRASH), signature backdoors (Carbanak/Anunak, Lizar/Diceloader), purchased/cracked commercial tooling (Cobalt Strike, Core Impact), and a productized EDR-killer (AvNeutralizer/AuKill) sold on criminal forums.
Attribution & motivation
- Sponsor / nation: Not a state-sponsored actor. FIN7 is an organized criminal enterprise assessed by multiple vendors to be Russian-speaking / Russia-based, with confirmed Ukrainian national members (per the 2018 U.S. DOJ indictment).
- Motivation: Financial. Early operations monetized stolen payment-card data sold on carding/darknet markets; later operations monetize via ransomware extortion (own RaaS brands and as a ransomware affiliate) and by selling intrusion tooling (e.g., the AvNeutralizer EDR killer) to other crews.
- Confidence: High for the activity cluster and financial motivation (corroborated by DOJ indictments/convictions and consistent CrowdStrike, Mandiant, Microsoft, SentinelOne, and Secureworks reporting). Note that the "Carbanak" backdoor has been used by more than one actor, so backdoor-only attributions to FIN7 should be treated with lower confidence than TTP-clustered attributions.
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 · 164 lines · 68 tokens per session scan B 63480393baf9
fin7-carbanak is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 12d ago), licensed Apache-2.0. It adds 68 tokens to every session and 5,942 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B 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.