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 UnboundCompute/security-agent-skills --skill hunting-nosql-operator-and-where-injectiongit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/hunting-nosql-operator-and-where-injection)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/hunting-nosql-operator-and-where-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-nosql-operator-and-where-injection/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/unboundcompute/security-agent-skills/hunting-nosql-operator-and-where-injection"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/hunting-nosql-operator-and-where-injection.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 | $0.00171 | $0.01952 |
| Opus 5 | $0.00086 | $0.00976 |
| Sonnet 5 | $0.00034 | $0.00390 |
| Haiku 4.5 | $0.00017 | $0.00195 |
Grade A, and why
hunting-nosql-operator-and-where-injection 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 7d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunting NoSQL operator and where injection: when a value arrives as an operator
NoSQL injection rarely looks like classic SQL injection because there is no string to concatenate.
Instead, a document store filter is often built directly from a request object, so if the attacker sends
an object where the code expected a scalar, its keys become query operators. A login check that compares a
password to a request field can be turned always-true by sending an operator that matches anything. Worse,
some stores evaluate server-side JavaScript, in a $where clause, a mapReduce function, or an aggregation
expression, and untrusted input reaching that path is code execution inside the database. You find these by
separating filters that bind scalar values from those that accept a request-shaped object or an expression,
and tracing untrusted input into the latter.
When to use
- Data access uses a document, key-value, or wide-column store with request-built query filters.
- A request field expected to be a scalar could arrive as an object whose keys become operators.
- Untrusted input can reach a server-side JavaScript evaluation:
$where, mapReduce, or an aggregation.
Scope check
Test NoSQL injection only against databases and applications you own or are authorized to assess, on non-production data. A confirming operator or expression can read or alter records outside the intended scope, so stay inside the authorized boundary. If you can't name the authorization, stop.
The loop
-
Establish the query sinks and split them. Inventory where the store is queried, then separate calls that bind scalar values from calls that accept a request-shaped filter object or evaluate a server-side expression. This is the false-positive killer: a query with typed scalar parameters cannot be operator- injected. Name the structure-accepting and expression-evaluating sinks first.
-
Trace untrusted input into filter objects. Follow request bodies and query strings into filters built from them. The key question is whether a field expected to be a scalar can arrive as an object: if the code does
find({ user: req.body.user })andreq.body.usercan be an object, the attacker sends an operator that changes the match. Confirm whether the value is type-checked to a scalar before use.
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.
- 7d ago First seen · 134 lines · 171 tokens per session scan A 5622a517d80f
hunting-nosql-operator-and-where-injection is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 171 tokens to every session and 1,952 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
api-11-nosql-injection
API NoSQL injection testing: MongoDB operator injection ($ne, $gt, $regex, $where), blind NoSQL via $regex character extraction, JSON body injection in REST APIs, and GraphQL NoSQLi via filter arguments. Use when testing APIs using MongoDB or other NoSQL databases.
nosqli
NoSQL injection — MongoDB operator injection ($ne, $gt, $where, $regex), CouchDB / Firebase / Redis attack patterns, auth bypass, blind extraction.
integrate-arcjet-guard-google-adk
Integrate Arcjet security into a Google ADK JS app using @arcjet/guard — put guardPlugin first on Runner({ plugins }) so beforeToolCallback gates tools, and read a caller-owned id from helper options or context. Use when asked to add Arcjet to Google ADK, @google/adk, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-mastra
Integrate Arcjet security into a Mastra agent using @arcjet/guard — wrap createTool execute, screen input/output with a Processor tripwire, and gate unwrapped MCP/workspace tools with hooks. Use when asked to add Arcjet to a Mastra agent, rate limit its tools, screen inbound messages, or block prompt injection / PII.
adr-skill
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…