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 profinetgit 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/profinet)<a href="https://agentmods.dev/skills/purpleailab/decepticon/profinet"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/profinet/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/profinet"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/profinet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Privilege Escalation · line 28 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 46 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 264 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00088 | $0.04864 |
| Opus 5.5 | $0.00035 | $0.01946 |
| Sonnet 5.5 | $0.00018 | $0.00973 |
| Haiku 4.5 | $0.00009 | $0.00486 |
Grade A, and why
profinet scanned grade A 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 1mo 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo tcpdump -i eth0 ether proto 0x8892 -c 20 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 — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROFINET Attack Playbook (EtherType 0x8892 / DCP)
PROFINET is the dominant European/Siemens fieldbus for deterministic real-time process automation — deployed in Siemens SIMATIC PLC networks, Beckhoff TwinCAT, Phoenix Contact, and virtually all post-2005 EU manufacturing. Unlike Modbus or EtherNet/IP, PROFINET RT operates at Layer 2 (EtherType 0x8892) — there is no IP header, no routing, and no firewall coverage at the IP layer. The attacker must be on the same Ethernet broadcast domain (OT L2 segment, or have a SPAN/TAP into it). DCP (Discovery and basic Configuration Protocol) provides unauthenticated device enumeration, naming, IP assignment, and factory-reset — all without credentials.
SAFETY FIRST
DCP Set commands (station-name reassignment, IP change, factory-reset) immediately disrupt the IO-controller ↔ IO-device association. When an IO-device loses its expected station name, the PROFINET IO controller goes to BF (Bus Fault) state and the process typically enters a safe/halt state or continues with the last-known values depending on watchdog configuration. This is a process-disruption event. Confirm written scope authorization before any DCP Set or RT frame injection. DCP Identify (read) is safe.
Prerequisites
- Physical or logical access to the OT L2 segment (direct port, rogue switch, SPAN, compromised HMI/engineering workstation on the same VLAN).
- Wireshark with
pn_dcpdissector (ships by default — filter:pn_dcp). - Python with
scapyfor DCP crafting (orpython-profinetlibrary).
# Verify interface sees PROFINET frames
sudo tcpdump -i eth0 ether proto 0x8892 -c 20
# If frames appear: you are on the OT segment
# Install scapy (already on Kali)
pip install scapy
# python-profinet (alternative higher-level library)
pip install profinet
Phase 1 — Discover: DCP Identify-All broadcast
DCP Identify-All is a Layer-2 broadcast to 01:0E:CF:00:00:00 (PROFINET multicast). All devices on the segment reply with their station name, IP, MAC, device type, vendor, order number, firmware.
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.
- 1mo ago First seen · 352 lines · 88 tokens per session scan A c99cd0fcf63b
profinet is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,286 stars, last pushed 3d ago), licensed Apache-2.0. It adds 88 tokens to every session and 4,864 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bun-ffi-native-binding
Build high-performance native modules for JavaScript using Bun's FFI (Foreign Function Interface) with Zig or C. Use when optimizing hot paths, integrating system libraries, or requiring native performance for compute-intensive operations.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors, served via preview URL.
onboarding
First run after the user saves their investing profile: import holdings and watchlists from the brokerage they connected or the screenshots they attached, then propose three first tasks (one on their portfolio or watchlist, one from their profile, one on today's market) and do the one they pick.
coder-agent
A code-generation agent that turns an algorithm design into executable code for GPU programming languages such as CUDA, Triton, and OpenCL. It also targets NVIDIA, AMD, and Intel hardware.
huawei-cloud-cloudrobo-dispatch
Manage CloudRobo embodied-agent task dispatch (robo-dispatcher) — create embodied tasks that drive a robot via an exec/model and constraints, list/show tasks in a session, cancel tasks, and retrieve task results. Dispatch orchestrates robots (robotid from cloudrobo-robot) with inference models (execmodelid from…