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-message-broker-topic-authorizationgit 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-message-broker-topic-authorization)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-message-broker-topic-authorization"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-message-broker-topic-authorization/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-message-broker-topic-authorization"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-message-broker-topic-authorization.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 | $0.00166 | $0.01982 |
| Opus 5 | $0.00083 | $0.00991 |
| Sonnet 5 | $0.00033 | $0.00396 |
| Haiku 4.5 | $0.00017 | $0.00198 |
Grade A, and why
auditing-message-broker-topic-authorization 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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing message-broker topic authorization: when a wildcard subscribes to everyone
A message broker is a shared channel that many producers and consumers, often many tenants, talk through, and topic authorization is what keeps one client's messages from reaching another's. That boundary is thinner than it looks. Authenticating to the broker is not the same as being authorized per topic: a broker that checks the connection but not the topic lets any authenticated client read or write any topic. Wildcards make it worse, a subscription with a wildcard can match another tenant's topics and receive their messages, and a broad publish permission can inject into a control or command topic that consumers act on. And on a shared broker, topic naming is frequently the only thing separating tenants, which is a convention, not an enforced boundary. The audit asks, for each client, exactly which topics it can publish to and subscribe to, and whether that matches its role. You audit this by enumerating effective topic permissions and testing cross-tenant reach.
When to use
- A broker (MQTT, Kafka, AMQP, or similar) carries messages across producer, consumer, or tenant boundaries.
- Clients authenticate to the broker but topic-level publish and subscribe authorization may be missing.
- Wildcard subscriptions or broad publish grants may cross topics or tenants on a shared broker.
Scope check
Test broker authorization only on brokers you own or are authorized to assess, on non-production topics. Subscribing or publishing exercises a live broker and can receive or inject real messages, so use non-production topics and never read another tenant's real messages or inject into a live command topic. If you can't name the authorization, stop.
The loop
- Establish each client's intended topics first. Name, per client or tenant, exactly which topics it should publish to and which it should subscribe to. This is the false-positive killer: a client authorized to precisely its own topics for precisely the direction it needs, with no wildcard crossing tenants, is correctly scoped. Name the intended topic map, then compare effective permissions to it.
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.
- 10d ago First seen · 138 lines · 166 tokens per session scan A d42bb55172a8
auditing-message-broker-topic-authorization is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed yesterday), licensed MIT. It adds 166 tokens to every session and 1,982 once invoked, about $0.0008 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
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, Astro, Nuxt, Bun, Deno, NestJS, or Node.js routes with rate limiting, bot detection, Shield, email validation, or sensitive info detection.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
fhir-developer-skill
FHIR API development guide for building healthcare endpoints. Use when: (1) Creating FHIR REST endpoints (Patient, Observation, Encounter, Condition, MedicationRequest), (2) Validating FHIR resources and returning proper HTTP status codes and error responses, (3) Implementing SMART on FHIR authorization and OAuth…
api-security
Reviews REST and GraphQL APIs against the OWASP API Security Top 10:2023. Auto-invoked when reviewing OpenAPI/Swagger specs, API endpoint code, or GraphQL schemas. Covers BOLA, BFLA, authentication, rate limiting, and SSRF. Produces findings mapped to API1-API10 with remediation guidance.
create-auth-skill
Scaffold and implement authentication in TypeScript/JavaScript apps using Better Auth. Detect frameworks, configure database adapters, set up route handlers, add OAuth providers, and create auth UI pages. Use when users want to add login, sign-up, or authentication to a new or existing project with Better Auth.
api-breaker
Automated API security testing starting from domains. Discovers REST, GraphQL, and SOAP APIs, reconstructs schemas, and tests for BOLA/IDOR, BFLA, mass assignment, JWT attacks, rate limiting bypass, and business logic flaws. Use when user asks to "test API security", "break API", "find API vulnerabilities", "test…