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 bloodhound-bhcegit 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/bloodhound-bhce)<a href="https://agentmods.dev/skills/purpleailab/decepticon/bloodhound-bhce"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bloodhound-bhce/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/bloodhound-bhce"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bloodhound-bhce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 2 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.
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 | $0.00061 | $0.01835 |
| Opus 5 | $0.00030 | $0.00918 |
| Sonnet 5 | $0.00012 | $0.00367 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
bloodhound-bhce 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BloodHound CE via Decepticon's bhce_* Tools
Decepticon ships a sidecar BloodHound Community Edition v9.2.2 stack
(see docs/adr/0005-bloodhound-via-bhce-rest-client.md). Three
@tool wrappers expose it to the agent:
| tool | what it does |
|---|---|
bhce_status |
Confirm BHCE is healthy and our HMAC token authenticates. Always call this first when an AD task starts. |
bhce_cypher |
Run any Cypher query against BHCE's graph. Mutations are off by default. |
bhce_ingest_zip |
Push a SharpHound .zip into BHCE — 3-step file-upload flow + polling until BHCE finishes parse + ESC* analysis. |
Use these instead of the legacy bh_ingest_zip / dcsync_check /
delegation_audit / gpo_audit / adcs_audit family — those are
the in-house port and are being retired per ADR-0005.
Why we use BHCE rather than our own ingest
BHCE's PostProcessedRelationships Go pipeline emits every edge a
red-team operator expects: ADCSESC1-13, GoldenCert, DCSync,
TrustedForNTAuth, IssuedSignedBy, CoerceAndRelayNTLMTo*,
HasSIDHistory, HasTrustKeys, SyncLAPSPassword, … The list is in
graphschema/ad/ad.go::PostProcessedRelationships() in the BHCE
source. We deliberately do not re-implement these in our
codebase; the agent leans on BHCE's analyzer instead.
The Decepticon KGStore still owns web, cloud, and smart-contract findings, and stays canonical for cross-domain chain planning. BHCE is the AD layer.
End-to-end loop the agent should follow
-
Health check —
bhce_status(). Verifyversion.data.server_versionmatches the deployed v9.2.2 andself.data.principal_nameis non-empty. If the diagnostic mentionsBHCE_URL/BHCE_TOKEN_*, the sidecar is offline or the token has been revoked — stop and report. -
Ingest — for every SharpHound collection drop:
bhce_ingest_zip(path="/abs/path/to/20260605_lab.zip")Expected result envelope:
{job_id, terminal_status, last_payload, elapsed_seconds}.terminal_statusmust be one ofComplete,PartiallyComplete,Failed,Cancelled. Anything else (anerrorfield, missing terminal_status) means BHCE never closed the job — surface the error to the operator rather than continuing with stale data.
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.
- 11d ago First seen · 144 lines · 61 tokens per session scan A a60922ec8882
bloodhound-bhce is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,835 once invoked, about $0.0003 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.
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.