Gemini Live API Dev
google-gemini/gemini-skills
A skill your agent uses when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live.
Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits.
Install Test Realtime Integrations
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful test-realtime-integrations --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .claude/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .claude/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrationsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful test-realtime-integrations --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .agents/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .agents/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful test-realtime-integrations --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .cursor/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .cursor/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cyberful/cyberful.git --path cyberful/builtin/skills/test-realtime-integrations--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful test-realtime-integrations --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .gemini/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .gemini/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cyberful/cyberful test-realtime-integrationsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .github/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .github/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .github/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cyberful/cyberful --skill test-realtime-integrations -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberful/cyberful test-realtime-integrations --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cyberful/builtin/skills/test-realtime-integrations .opencode/skills/test-realtime-integrations && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "test-realtime-integrations" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/test-realtime-integrations into .opencode/skills/test-realtime-integrations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-realtime-integrations", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
test-realtime-integrations- GitHub stars
- 135
- Token cost
- ~1.2k tokens
- SKILL.md length
- 456 words
- Files
- 10 (incl. scripts, references, assets)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits.
- Handshake and message authorization
- SKILL.md covers Model Connection, Channel, and…, Build a Protocol State Matrix, Prove Isolation and Test Integrity and Freshness, plus 1 more section
- Runs Python scripts from its folder
- Cross-site WebSocket hijacking
What it does
Test Realtime Integrations is an agent skill from cyberful/cyberful. Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits. Use for handshake and message authorization, cross-site WebSocket hijacking, channel isolation, replay, ordering, signature verification, canonicalization, event forgery, subscription leaks, retry behavior, and integration confused deputies.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/realtime-probe-evidence.schema.json` and `assets/realtime-probe.example.json`).
It sits in Backend & APIs, covering Realtime and WebSockets, Webhooks and Async programming. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.
When your agent uses it
- Handshake and message authorization
- Cross-site WebSocket hijacking
- Channel isolation
- Signature verification
Example prompts
- “/test-realtime-integrations”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit ec598a6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Test Realtime Integrations loads about 1.2k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 107 tokens; SKILL.md has 456 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 456 words, ~1,215 tokens.
Download SKILL.mdSave it as
.claude/skills/test-realtime-integrations/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.- name
- test-realtime-integrations
- description
- Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits. Use for handshake and message authorization, cross-site WebSocket hijacking, channel isolation, replay, ordering, signature verification, canonicalization, event forgery, subscription leaks, retry behavior, and integration confused deputies.
- metadata.domain
- application-security
- metadata.subdomain
- realtime-integrations
- metadata.triggers
- websocket authorization, server-sent events, webhook signature verification, event replay, channel isolation, asynchronous callback security
- metadata.tags
- websocket, sse, webhook, event-stream, replay, message-authorization
Test Realtime and Event Integrations
Model Connection, Channel, and Event Authority
Separate authentication and authorization at:
- transport handshake;
- connection establishment;
- subscription or channel join;
- each inbound command;
- each outbound event;
- reconnect and resume;
- asynchronous delivery and replay.
Record principal, tenant, origin, token source, channel key, object relationship, message type, sequence, and state. A connection authenticated once can still cross authorization boundaries as roles, tenants, or object ownership change.
Read websocket-sse.md for bidirectional and streaming channels. Read webhook-events.md for signed callbacks, ordering, and retries.
Build a Protocol State Matrix
Capture the normal sequence and then vary one dimension: send before subscribe, subscribe before authentication, change tenant mid-connection, reuse a resume token, reorder frames, duplicate events, omit fields, add unknown fields, and reconnect after revocation.
Compare UI-generated traffic with direct protocol messages. Client code frequently hides message types, sequence fields, channel selectors, and administrative actions.
Prove Isolation
Use two controlled principals and at least two tenants or resource owners. Test predictable and observed channel identifiers, wildcard subscriptions, filter changes, batch subscriptions, history endpoints, presence lists, typing indicators, error messages, and compressed frames.
For server push, verify that each publication is authorized against current state or a correctly invalidated authorization snapshot.
Test Integrity and Freshness
For webhooks and callbacks, verify signature construction, canonical bytes, algorithm and key selection, timestamp window, nonce or event ID, replay storage, secret rotation, destination binding, and verification before parsing or side effects.
For queues and event streams, test duplicate delivery, out-of-order delivery, poison messages, partial failure, redrive, schema evolution, and event provenance.
For a small discriminating active set, use scripts/run_realtime_probe.py only after origins, request ceiling, rate, timeout, and authorization reference are explicit. Copy assets/realtime-probe.example.json, preserve assets/realtime-probe.schema.json, and keep credentials or signatures only in the environment variables declared by scripts/manifest.json. Never place authorization, cookie, proxy-authorization, transport configuration, or any declared secret header value in the JSON header map.
Show full SKILL.md (147 more words)Show less
The runner validates the complete probe set before resolving secret environment values or issuing the first request. Exact origins and limits are defense in depth and never grant authority. Literal loopback targets run direct with proxies disabled; every other target requires the host-owned HTTP(S) proxy and CA route described by scripts/manifest.json. Missing transport refuses before connection, TLS verification is never disabled, and bounded, secret-redacted raw evidence conforms to assets/realtime-probe-evidence.schema.json. The runner terminates the full process group as soon as a stream, response, or global deadline boundary is crossed. It performs webhook and callback requests plus bounded SSE or WebSocket handshakes; use ZAP or the approved protocol runtime for stateful message exchange.
Report the Failing Boundary
Document transport state, message or event, principal and channel mapping, ordering prerequisites, current versus stale authorization, and durable effect. Recommend message-level authorization, explicit schema, replay controls, transactional consumption, and bounded connection resources.
© cyberful, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 9 other files (scripts, references, assets) in cyberful/builtin/skills/test-realtime-integrations of cyberful/cyberful.
- SKILL.md
- agents/openai.yaml
- assets/realtime-probe-evidence.schema.json
- assets/realtime-probe.example.json
- assets/realtime-probe.schema.json
- references/webhook-events.md
- references/websocket-sse.md
- scripts/manifest.json
- scripts/run_realtime_probe.py
- tests/test_run_realtime_probe.py
Open the folder on GitHubat commit ec598a6
Compare with similar skills
Test Realtime Integrations next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Test Realtime Integrations this skillcyberful/cyberful | 135 | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | |
| Gemini Live API Devgoogle-gemini/gemini-skills | 4.3k | — | ~4.6k | Automated safety check: Pass | Apache-2.0 | |
| Tiger Brokers Rust SDKqusong0627/QuantMind | 1.7k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Neon Functionsneondatabase/agent-skills | 100 | — | ~12k | Automated safety check: Notes | Apache-2.0 | |
| Helius for Solanainternet-court/internet-court-skill | 6.4k | 2 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Fishjam JS Server SDKsoftware-mansion-labs/skills | 291 | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
- Official
Tiger Brokers Rust SDK
qusong0627/QuantMind
Reference guides for building Rust apps on the Tiger Brokers OpenAPI SDK: setup, async market data, orders, accounts, options and real-time push.
- Official
Neon Functions
neondatabase/agent-skills
Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASEURL injected automatically and compute that runs next to your data.
Helius for Solana
internet-court/internet-court-skill
Guides building Solana apps on Helius: sending transactions, asset and NFT queries, live streaming, webhooks, priority fees, wallet analysis and API key onboarding.
Fishjam JS Server SDK
software-mansion-labs/skills
Node.js / TypeScript server SDK for Fishjam — backends that create rooms, mint peer tokens, listen to server notifications, and run agents.
iOS Networking
dpearson2699/swift-ios-skills
Build, review, or improve networking code in iOS/macOS apps using URLSession with async/await, structured concurrency, and modern Swift patterns.
More from cyberful/cyberful
All 85 skills in this repoAudit Infrastructure As Code
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
Audit Kubernetes Policy Enforcement
cyberful/cyberful
Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.
Audit Pci Dss Penetration Test Evidence
cyberful/cyberful
Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.
Operate Content Discovery
cyberful/cyberful
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
Operate Network Recon
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
Operate Sast Toolchain
cyberful/cyberful
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Related
Categories
Questions about Test Realtime Integrations
What does Test Realtime Integrations do?
Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits. Test Realtime Integrations is an agent skill from cyberful/cyberful. Assess WebSocket, Server-Sent Events, webhook, event-stream, callback, and asynchronous integration security during authorized penetration tests or code audits.
When should I use Test Realtime Integrations?
Test Realtime Integrations fits situations like: handshake and message authorization; cross-site WebSocket hijacking; channel isolation; signature verification.
How do I install Test Realtime Integrations in Claude Code?
Run `npx skills add cyberful/cyberful --skill test-realtime-integrations -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/test-realtime-integrations in cyberful/cyberful) into .claude/skills/test-realtime-integrations in your project. Claude Code loads it when a task matches its description.
How do I install Test Realtime Integrations in Codex?
Run `npx skills add cyberful/cyberful --skill test-realtime-integrations -a codex`. Or copy the skill folder (cyberful/builtin/skills/test-realtime-integrations in cyberful/cyberful) into .agents/skills/test-realtime-integrations in your project. Codex loads it when a task matches its description.
Can I use Test Realtime Integrations in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cyberful/cyberful --skill test-realtime-integrations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-realtime-integrations, .gemini/skills/test-realtime-integrations, .github/skills/test-realtime-integrations and .opencode/skills/test-realtime-integrations in your project.
What does Test Realtime Integrations need to run?
Going by SKILL.md and its folder, Test Realtime Integrations needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Test Realtime Integrations access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Test Realtime Integrations safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Test Realtime Integrations use?
Test Realtime Integrations is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Test Realtime Integrations use?
About 1.2k tokens (SKILL.md is roughly 4.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.
What are the alternatives to Test Realtime Integrations?
Skills that share tags, products or a category with Test Realtime Integrations: Gemini Live API Dev (google-gemini/gemini-skills, 4.3k stars), Tiger Brokers Rust SDK (qusong0627/QuantMind, 1.7k stars), Neon Functions (neondatabase/agent-skills, 100 stars) and Helius for Solana (internet-court/internet-court-skill, 6.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Test Realtime Integrations?
cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.
Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.