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-querygit 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-query)<a href="https://agentmods.dev/skills/purpleailab/decepticon/bloodhound-query"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bloodhound-query/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-query"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/bloodhound-query.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 | $0.00032 | $0.01100 |
| Opus 5 | $0.00016 | $0.00550 |
| Sonnet 5 | $0.00006 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
bloodhound-query 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- bloodhound-query — 94% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BloodHound Query Playbook
1. Collect
# Python collector (works from Linux attacker box)
bloodhound-python -u USER -p 'PASS' -d DOMAIN -c all --zip --dns-tcp \
-ns DC_IP -o /workspace/bh.zip
# Or SharpHound from a Windows beachhead
# Invoke-BloodHound -CollectionMethod All -ZipFileName bh.zip
If bloodhound-python errors on TLS, add -gc gc.domain.local for the
global catalog FQDN.
2. Ingest into Decepticon KG
bh_ingest_zip("/workspace/bh.zip")
This populates User / Computer / Group / GPO / OU nodes with attribute properties (hasspn, dontreqpreauth, enabled, admincount, sidhistory).
3. Canonical Cypher queries
Run via bh_cypher("<query>") or post-process kg_query(kind=...):
| Goal | Cypher |
|---|---|
| Owned principals | MATCH (u) WHERE u.owned=true RETURN u.name |
| Shortest path to DA | MATCH p=shortestPath((u {owned:true})-[*1..]->(g:Group {name:'DOMAIN ADMINS@DOM'})) RETURN p |
| Kerberoastable users | MATCH (u:User {hasspn:true, enabled:true}) RETURN u.name,u.spns |
| AS-REP roastable | MATCH (u:User {dontreqpreauth:true, enabled:true}) RETURN u.name |
| DCSync candidates | `MATCH (n)-[:GetChanges |
| Unconstrained delegation | MATCH (c:Computer {unconstraineddelegation:true}) RETURN c.name |
| RBCD targets | MATCH (n)-[:AddAllowedToAct]->(c:Computer) RETURN n.name,c.name |
| GenericAll on user | MATCH (n)-[:GenericAll]->(u:User) WHERE NOT n=u RETURN n.name,u.name |
| ACL path to high-value | `MATCH p=shortestPath((u {owned:true})-[:GenericAll |
| Sessions on DC | MATCH (u:User)-[:HasSession]->(c:Computer) WHERE c.name CONTAINS 'DC' RETURN u.name,c.name |
| Computers w/ admin from owned | MATCH (u {owned:true})-[:AdminTo*1..2]->(c:Computer) RETURN c.name |
| GPO abuse | MATCH (n)-[:GpLink]->(:OU)-[:Contains*1..]->(c:Computer) WHERE n.name CONTAINS 'unsafe' RETURN n.name,c.name |
4. Auto-prioritize attack paths
After ingest:
plan_attack_chains(promote=True)
This walks the graph from owned → high-value and surfaces:
- Tier-0 reachability (DA / EA / krbtgt)
- Tier-1 reachability (server admins, backup ops)
- Lateral hops (admin → admin via AdminTo)
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 · 87 lines · 32 tokens per session scan A 05d6f5ffa26f
bloodhound-query is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,482 stars, last pushed 11d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,100 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
optimizing-ef-core-queries
Optimize Entity Framework Core queries by fixing N+1 problems, choosing correct tracking modes, using compiled queries, and avoiding common performance traps. Use when EF Core queries are slow, generating excessive SQL, or causing high database load.
golang-database
Comprehensive guide for Go database access. Covers parameterized queries, struct scanning, NULLable column handling, error patterns, transactions, isolation levels, SELECT FOR UPDATE, connection pool, batch processing, context propagation, and migration tooling. Use this skill whenever writing, reviewing, or debugging…
postgresql-table-design
Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
sql-optimization-patterns
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.
stale-sweep
Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…