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-websocket-connection-trustgit 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-websocket-connection-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-websocket-connection-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-websocket-connection-trust/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-websocket-connection-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-websocket-connection-trust.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 | $0.00190 | $0.02076 |
| Opus 5.5 | $0.00076 | $0.00830 |
| Sonnet 5.5 | $0.00038 | $0.00415 |
| Haiku 4.5 | $0.00019 | $0.00208 |
Grade A, and why
auditing-websocket-connection-trust 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing WebSocket connection trust: trust checked once at the upgrade, never per message
A WebSocket endpoint fails where it establishes trust once, at the upgrade, and never re-checks it. If the handshake authenticates purely from an ambient cookie and does not validate the origin, any web page can open an authenticated socket on the user's behalf (cross-site hijacking); if it authenticates at the handshake but never authorizes individual messages, a connection can escalate mid-stream. You audit it by resolving how the handshake authenticates (an ambient cookie, or an unpredictable token a cross-site page cannot read) and whether the origin is enforced, then following each privileged message to see whether it is re-authorized. A known false-positive trap lives here: an origin check delegated to a proxy is only a defense if the proxy actually rejects, so confirm the backstop. The wss certificate check belongs to the transport skill.
When to use
- You are reviewing a WebSocket upgrade handler, its origin check, and its per-message dispatch.
- The endpoint authenticates at the handshake, from a cookie or a token, and then handles messages.
- You want to know whether a cross-site page or a later message can drive a privileged action.
Scope check
Audit only endpoints you own or are authorized to assess, and open a socket or send a message only against a service in scope, a privileged message drives real state. Adjudicate on the handshake and the dispatch. If you can't name the authorization, stop.
The loop
- Resolve the origin check and the credential source first. Determine how the handshake authenticates: an ambient session cookie sent automatically by the browser, or an unpredictable per-connection token (a ticket, a bearer in a subprotocol or query) that a cross-site page cannot read. Then determine whether the origin is validated on the upgrade, and where. Ambient credentials plus a missing origin check is the cross-site-hijacking precondition, so settle both before flagging.
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.
- 1mo ago First seen · 140 lines · 190 tokens per session scan A ddcf55a5c6a1
auditing-websocket-connection-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 2,076 once invoked, about $0.0008 per session on Opus 5.5. 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
integrate-arcjet-guard-cloudflare-think
Integrate Arcjet security into a Cloudflare Think app using @arcjet/guard — assign guardHooks().beforeToolCall on a Think subclass so the hook gates tools, and read a caller-owned id from helper options. Use when asked to add Arcjet to Cloudflare Think, @cloudflare/think, rate limit its tools, screen inbound messages…
protect
Add Arcjet request protection to JavaScript and TypeScript HTTP handlers. Use when protecting Next.js, Express, Fastify, SvelteKit, Remix, React Router, Hono, 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.