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 auditing-datastore-exposure-and-abusegit 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/auditing-datastore-exposure-and-abuse)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-datastore-exposure-and-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-datastore-exposure-and-abuse/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/auditing-datastore-exposure-and-abuse"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-datastore-exposure-and-abuse.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 | $0.00175 | $0.02042 |
| Opus 5 | $0.00088 | $0.01021 |
| Sonnet 5 | $0.00035 | $0.00408 |
| Haiku 4.5 | $0.00017 | $0.00204 |
Grade A, and why
auditing-datastore-exposure-and-abuse 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.
Auditing datastore exposure and abuse: when the cache is an unauthenticated shell
Cache and key-value stores such as Redis and memcached are built for speed inside a trusted network, and that assumption is exactly what makes them dangerous when it does not hold. Two failures dominate. First, exposure: an instance bound to a reachable interface with no authentication is an open command interface, and on some stores the command set reaches configuration changes, on-disk file rewrites, module loading, and scripting, so an open port is a path to code execution, not just data theft. Second, command abuse: when an application composes datastore commands from untrusted input, the attacker can inject extra commands or reach a scripting or administrative command the application never intended. You audit both by checking how the instance is reached and how commands are composed.
When to use
- An application talks to a cache or key-value store such as Redis or memcached.
- A datastore instance may be bound to a reachable interface or lack authentication.
- Untrusted input reaches the command layer, a scripting evaluation, or a key or command name.
Scope check
Test datastore exposure and abuse only against instances and applications you own or are authorized to assess, on non-production data. A confirming command can change configuration, write files, or run a script on the host, so treat every proof as a live intrusion inside the authorized scope. If you can't name the authorization, stop.
The loop
- Establish the reachability and the command sinks first. Determine how each datastore instance is reached (bind address, network exposure, authentication requirement) and inventory where the application composes commands, including any scripting evaluation and any use of administrative or config commands. This is the false-positive killer: an instance bound to loopback or an authenticated private network with commands built from fixed templates and bound values is not the bug. Name the reachability and the sinks first.
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 · 175 tokens per session scan A 62a9a234de71
auditing-datastore-exposure-and-abuse is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 175 tokens to every session and 2,042 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 2026-08-31.
Other skills, from other repositories
audit-caching
Caching correctness checklist. Use when reviewing caches — keys missing a user/tenant dimension, stale data after writes, cache stampede, cached errors, or per-user responses landing in a shared or CDN cache.
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…
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…
terraform-skill
Terraform infrastructure as code best practices.