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 pink-sandstormgit 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/pink-sandstorm)<a href="https://agentmods.dev/skills/purpleailab/decepticon/pink-sandstorm"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/pink-sandstorm/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/pink-sandstorm"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/pink-sandstorm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 14 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 | $0.00060 | $0.05440 |
| Opus 5 | $0.00030 | $0.02720 |
| Sonnet 5 | $0.00012 | $0.01088 |
| Haiku 4.5 | $0.00006 | $0.00544 |
Grade A, and why
pink-sandstorm-agrius 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 12d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pink Sandstorm (Agrius, Agonizing Serpens, BlackShadow) — Adversary Emulation Profile
Pink Sandstorm (MITRE ATT&CK G1030) is an Iranian threat actor active since at least 2020, linked to Iran's Ministry of Intelligence and Security (MOIS). The group is notable for a series of destructive wiper and pseudo-ransomware operations primarily targeting Israeli organizations, with secondary operations against targets in the UAE, South Africa, and Hong Kong. Agrius deliberately disguises destructive wiper attacks as ransomware, using extortion personas (BlackShadow, Moneybird, n3tw0rm) to mask its true intent — strategic disruption and data destruction aligned with Iranian state interests. The group operates a lineage of custom .NET and C++ wipers (Apostle → Fantasy → MultiLayer → BFG Agonizer) alongside the IPsec Helper backdoor, ASPXSpy web shells, and public offensive tools (Mimikatz, Plink, NBTscan). Since the October 2023 Israel-Hamas war, Microsoft has observed Pink Sandstorm collaborating with Hezbollah cyber units and escalating hack-and-leak operations against Israeli targets.
Attribution & motivation
- Sponsor / nation: Islamic Republic of Iran — Ministry of Intelligence and Security (MOIS). Microsoft's 2023 Iran threat report formally linked Pink Sandstorm / AMERICIUM to MOIS operations. The group operates under multiple extortion personas: BlackShadow (Shirbit, 2020), Justice Blade, Malek Team, and Moneybird.
- Motivation: Primarily destructive / disruptive operations — wiping data and rendering systems inoperable while masquerading as financially motivated ransomware. Secondary motivations include espionage and data theft (PII, intellectual property, database exfiltration) and hack-and-leak influence operations designed to cause political embarrassment and societal disruption in Israel.
- Attribution confidence: High. Backed by Microsoft threat intelligence formal attribution (AMERICIUM / Pink Sandstorm → MOIS), SentinelOne (Agrius lineage), Check Point (Moneybird), ESET (Fantasy supply-chain), and Palo Alto Unit 42 (Agonizing Serpens) consistent reporting. Code-level overlaps across Apostle, Fantasy, IPsec Helper, MultiLayer, and DEADWOOD confirm a single actor operating under rotating aliases.
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.
- 12d ago First seen · 181 lines · 60 tokens per session scan A 3bab1f116586
pink-sandstorm-agrius is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 12d ago), licensed Apache-2.0. It adds 60 tokens to every session and 5,440 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.