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 apt33-elfingit 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/apt33-elfin)<a href="https://agentmods.dev/skills/purpleailab/decepticon/apt33-elfin"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt33-elfin/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/apt33-elfin"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/apt33-elfin.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 67 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 119 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 | $0.00055 | $0.04357 |
| Opus 5 | $0.00028 | $0.02178 |
| Sonnet 5 | $0.00011 | $0.00871 |
| Haiku 4.5 | $0.00006 | $0.00436 |
Grade A, and why
apt33-elfin 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APT33 (Elfin, Peach Sandstorm, HOLMIUM) — Adversary Emulation Profile
APT33 (MITRE ATT&CK G0064; aliases Elfin, Peach Sandstorm, HOLMIUM) is a suspected Iranian state-sponsored threat group that has conducted cyber-espionage operations since at least 2013. The group is best known for spearphishing-driven intrusions against the aviation, energy, and petrochemical sectors in the United States, Saudi Arabia, and South Korea, and for an enduring evolution from .hta-based phishing toward large-scale cloud-identity attacks. Its operations blend publicly available offensive tooling with custom backdoors, and the group has been linked — with varying confidence — to destructive wiper malware. This profile maps APT33's documented TTPs to ATT&CK and provides emulation guidance for Decepticon under authorized engagement scope.
Attribution & motivation
- Suspected sponsor / nation: Iran. FireEye/Mandiant assessed APT33 works at the behest of the Iranian government and reported evidence linking the group to the Nasr Institute, an Iranian organization associated with cyber-warfare operations. Microsoft tracks the same actor as Peach Sandstorm and likewise attributes it to Iranian state interests.
- Primary motivation: Strategic espionage / intelligence collection aligned with Iranian state interests (aerospace, defense, energy). Microsoft assessed the 2023 password-spray campaign was likely intended to facilitate intelligence collection supporting Iranian state objectives.
- Secondary / destructive dimension: APT33 has been linked to the StoneDrill wiper, which shares similarities with the Shamoon family used against Saudi Aramco and RasGas (2012). Confidence on the destructive link is lower than the espionage attribution — Kaspersky and FireEye both noted it is unproven whether the Shamoon and StoneDrill operators are the same group or merely aligned in interests/region. Treat any destructive capability claim as plausible-but-unconfirmed.
- Attribution confidence: Moderate-to-high for Iranian state-sponsored espionage (multiple independent vendors converge: FireEye/Mandiant, Symantec, Microsoft). Lower for the destructive/wiper attribution.
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 · 149 lines · 55 tokens per session scan A 98f87dbfe461
apt33-elfin 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 4,357 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…