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 apt34-oilriggit 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/apt34-oilrig)<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt34-oilrig"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt34-oilrig/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/apt34-oilrig"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt34-oilrig.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 132 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 27 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 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.
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 | $0.00052 | $0.05397 |
| Opus 5 | $0.00026 | $0.02698 |
| Sonnet 5 | $0.00010 | $0.01079 |
| Haiku 4.5 | $0.00005 | $0.00540 |
Grade A, and why
apt34-oilrig 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APT34 (OilRig, Helix Kitten, Hazel Sandstorm) — Adversary Emulation Profile
APT34 — tracked as OilRig, Helix Kitten, Hazel Sandstorm, Earth Simnavaz, Crambus, Cobalt Gypsy / COBALT GYPSY, IRN2, Evasive Serpens, EUROPIUM, ITG13, and TA452 (MITRE ATT&CK G0049) — is a suspected Iranian state-sponsored cyber-espionage group operational since at least 2014. It conducts long-running, reconnaissance-heavy intrusions against Middle Eastern and international organizations, favoring spearphishing for initial access, heavy use of PowerShell/VBScript backdoors, custom DNS-tunneling C2, supply-chain and trust-relationship abuse, and patient credential harvesting. The group continually re-tools (BONDUPDATER → SideTwist → cloud/Exchange-based C2) and is notable for living-off-the-land tradecraft, password-filter-DLL credential capture, and exfiltrating data through victim-owned Microsoft Exchange servers to blend with legitimate mail flow.
Attribution & motivation
- Suspected sponsor: Iran. FireEye/Mandiant assesses APT34 "works on behalf of the Iranian government based on infrastructure details that contain references to Iran, use of Iranian infrastructure, and targeting that aligns with nation-state interests." Multiple vendors (Trend Micro, Microsoft, CrowdStrike) link the cluster to Iranian intelligence services.
- Motivation: Strategic cyber espionage — long-term reconnaissance and credential/data theft to advance Iranian geopolitical interests in the region. Primary intent is intelligence collection, not financial gain. (A separate but related Iranian destructive operation, ZeroCleare wiper (S1151), is associated with the same cluster, indicating latent destructive capability.)
- Confidence: High that the activity is Iranian state-aligned espionage; the precise sponsoring agency varies by vendor naming. Attribution of any single intrusion should be treated as suspected unless backed by collected infrastructure/tooling overlap.
Targeting
- Sectors: Financial/banking, government, energy/oil & gas, chemical, telecommunications, critical infrastructure, and aviation/transport.
- Regions: Primarily the Middle East — Gulf Cooperation Council states (UAE, Saudi Arabia, Kuwait, Qatar, Bahrain), plus Israel; with international reach into the U.S. and other regions via supply-chain and trust-relationship pivots.
- Victim profile: Government ministries and state-aligned enterprises in strategic sectors; the group frequently compromises one organization (e.g., HR/job portals, telecoms) and abuses that trust to reach higher-value government targets.
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 · 165 lines · 52 tokens per session scan A 074bac56a049
apt34-oilrig is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 52 tokens to every session and 5,397 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…