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 ersinkoc/security-check --skill sc-nosqligit clone --depth 1 https://github.com/ersinkoc/security-checkWrote 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/ersinkoc/security-check/sc-nosqli)<a href="https://agentmods.dev/skills/ersinkoc/security-check/sc-nosqli"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-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/ersinkoc/security-check/sc-nosqli"><img src="https://agentmods.dev/badge/skills/ersinkoc/security-check/sc-nosqli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00019 | $0.01592 |
| Opus 5 | $0.00010 | $0.00796 |
| Sonnet 5 | $0.00004 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
sc-nosqli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC: NoSQL Injection
Purpose
Detects NoSQL injection vulnerabilities where user-controlled input manipulates NoSQL database queries. Unlike SQL injection, NoSQL injection exploits operator injection, JSON structure manipulation, and JavaScript execution within query contexts. Covers MongoDB, Redis, CouchDB, DynamoDB, and Elasticsearch.
Activation
Called by sc-orchestrator during Phase 2. Runs when NoSQL databases are detected in the architecture.
Phase 1: Discovery
File Patterns to Search
**/*.ts, **/*.js, **/*.py, **/*.php, **/*.java, **/*.go, **/*.cs,
**/models/*, **/controllers/*, **/services/*, **/repositories/*,
**/*mongo*, **/*redis*, **/*elastic*, **/*couch*, **/*dynamo*
Keyword Patterns to Search
# MongoDB
"find(", "findOne(", "findOneAndUpdate(", "findOneAndDelete(",
"aggregate(", "updateOne(", "updateMany(", "deleteOne(", "deleteMany(",
"$where", "$regex", "$gt", "$gte", "$lt", "$lte", "$ne", "$in", "$nin",
"$or", "$and", "$not", "$exists", "$expr",
"MongoClient", "mongoose.model", "collection.find"
# Redis
"redis.get(", "redis.set(", "redis.eval(", "redis.send_command(",
"EVAL ", "EVALSHA", "redis.call("
# Elasticsearch
"client.search(", "client.index(", "query_string",
"script_score", "painless", "elasticsearch"
# CouchDB
"_find", "mango", "cloudant"
Data Flow Tracing
Sources: HTTP request body (JSON), query parameters, headers, cookies
Sinks:
- MongoDB:
collection.find(),collection.findOne(),Model.find(),aggregate()— when query object is constructed from user input - Redis:
EVALwith user input in script,redis.send_command()with dynamic commands - Elasticsearch:
query_stringquery with user input,scriptfields with user input
Phase 2: Verification
Exploitability Checklist
- Can the attacker inject MongoDB operators (
$gt,$ne,$regex,$where) into the query? - Can the attacker modify the query structure by injecting JSON keys?
- Can the attacker inject JavaScript code into
$whereor$functionexpressions? - Is the request body parsed as JSON and passed directly to the database driver?
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.
- 9d ago First seen · 181 lines · 19 tokens per session scan A 8d5d2e8175e3
sc-nosqli is a skill published in the GitHub repository ersinkoc/security-check (56 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 1,592 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hunt-nosqli
Hunt NoSQL Injection — MongoDB operator injection ($where, $regex, $gt, $ne), CouchDB, Redis command injection, auth bypass via NoSQLi, data dump. Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages.
managed-db-services
Configure DigitalOcean Managed MySQL, MongoDB, Valkey, Kafka, and OpenSearch for App Platform. Use when setting up non-PostgreSQL databases, configuring trusted sources, or troubleshooting database connectivity.
data-nosql-database
Use this skill when asked about MongoDB, Cassandra, DynamoDB, Couchbase, CosmosDB, NoSQL, document database, wide-column, key-value, consistency model, CAP theorem, sharding, or denormalization. This skill enforces: NoSQL type selection (document, key-value, wide-column, graph), MongoDB aggregation pipeline and…
huawei-dds-dcs
Use when creating or managing Document Database Service (DDS/MongoDB-compatible) or Distributed Cache Service (DCS/Redis/Memcached) on Huawei Cloud. Triggers: DDS, DCS, MongoDB, Redis, Memcached, document DB, cache, replica set, sharding. NOT for: RDS (use huawei-rds), GaussDB (use huawei-gaussdb).
dotnet-testing-advanced-testcontainers-nosql
Guidance for integration tests using Testcontainers with MongoDB, a document database, and Redis, an in-memory key-value database.
kit-nosql
NoSQL guardrails pack — MongoDB $set/replace and schema drift, Redis SCAN/TTL/atomicity, eventual consistency. Use when writing MongoDB, Redis, DynamoDB, or other non-relational store code.