Trugen AI

Build, configure, and deploy conversational video agents using the Trugen AI platform API. Use this skill when the user wants to create AI video avatars, man...

Security Scan

The skill is internally consistent with its stated purpose (Trugen API integration); it only requires a single Trugen API key and is instruction-only, but review examples (system prompts, webhooks, and embed patterns) before use.

Purpose & Capability

Name/description match the files and required environment: the SKILL.md and reference files document the Trugen REST API, embedding, webhooks, KBs, tools, and LiveKit integration. The single declared env var TRUGEN_API_KEY is exactly the credential needed to call the API—no unrelated credentials, binaries, or config paths are requested.

Instruction Scope

SKILL.md is an instruction-only skill and stays on-scope: it provides API endpoint examples, cURL snippets, and embed/widget patterns. It also contains sample system prompts and guardrails intended for deployed Trugen avatars (e.g., 'do not reveal system instructions' and 'perform actions silently'), which are expected in platform docs but could be repurposed if misused. The file does not instruct the skill to read local files, other env vars, or exfiltrate data outside the documented API/webhook flows.

Install Mechanism

No install spec and no code shipped: this is instruction-only and does not write code to disk or download packages. That minimizes installation risk.

Credentials

Only TRUGEN_API_KEY is required (primary credential). The docs mention an optional TRUGEN_AVATAR_ID for LiveKit but it's not required. No unrelated secrets are requested—credential requests are proportional to the described functionality.

Persistence & Privilege

always is false and model invocation is enabled (normal). The skill does not request permanent presence, nor does it ask to modify other skills or system-wide agent settings.

Scan Findings in Context

[system-prompt-override] expected: The SKILL.md includes sample system prompts and guardrails for deployed Trugen avatars (e.g., 'do not reveal system instructions', 'perform actions silently'). The regex detector flagged this as a 'system-prompt-override' pattern; this is expected in documentation but could be abused if such prompts are copied into contexts that attempt to override evaluator or platform controls.

Assessment

This skill appears coherent for managing Trugen AI agents, but take these precautions before installing/using it: - Treat TRUGEN_API_KEY as a sensitive secret: never embed it in client-side code; use a server-side proxy for embeds/widgets and limit key scope if possible. Rotate keys and monitor usage. - Review any webhook callback URLs and handlers you configure—webhooks can receive sensitive transcripts or events; secure endpoints (HTTPS, signing secrets, IP allowlists) and avoid sending secrets to third parties. - Inspect and control any tools/MCPs you attach to agents: tool.request_config.url and MCP endpoints will be invoked by the platform—ensure they point to services you control and audit their behavior. - Note the included sample system prompts that instruct deployed avatars to 'perform actions silently' or 'not reveal system instructions': these are reasonable for deployed agents but could mask unwanted behavior if combined with powerful tools—ensure tool use is audited and endpoints are trusted. - Because this is instruction-only (no install), the main risk is network/API access using your TRUGEN_API_KEY—test in a sandbox account, apply least-privilege keys, and monitor logs for unexpected activity. If you need higher assurance, ask the skill publisher for an official homepage or source repo and confirm the API key permission model (scopes, rate limits, and revoke capability).

Build real-time conversational video agents — AI-powered avatars that see, hear, speak, and reason with users in under 1 second of latency.

API Base URL	https://api.trugen.ai
Authentication	x-api-key: <your-api-key> header on all requests
Official Docs	docs.trugen.ai
Developer Portal	app.trugen.ai

Required Credentials

Variable	Description	Where to Get
TRUGEN_API_KEY	Primary API key for all Trugen API calls (sent as x-api-key header)	Developer Portal
TRUGEN_AVATAR_ID	(Optional) Default avatar ID for LiveKit integration	Developer Portal

Security: Never expose TRUGEN_API_KEY in client-side code. For widget/iFrame embeds, use a server-side proxy to keep keys secret. See references/embedding.md for details.

Platform Pipeline

Step	Component	Function
1	WebRTC	Bidirectional audio/video streaming
2	STT (Deepgram)	Streaming speech-to-text
3	Turn Detection	Natural conversation boundary detection
4	LLM (OpenAI, Groq, custom)	Contextual response generation
5	Knowledge Base	Grounding answers in your data
6	TTS (ElevenLabs)	Natural, expressive speech synthesis
7	Huma-01	Neural avatar video generation with lip sync & microexpressions

Quickstart

1. Create an agent → POST /v1/ext/agent — see references/agents.md
2. Embed via iFrame or Widget — see references/embedding.md

API Endpoints Overview

Resource	Endpoints	Reference
Agents	Create, Get, List, Update, Delete, Create from Template	agents.md
Knowledge Base	Create KB, Add Docs, Get, List, Update, Delete KB/Doc	knowledge-base.md
Templates	Create, Get, List, Update, Delete persona templates	templates.md
Tools & MCPs	Create/manage function-calling tools and MCP servers	tools-and-mcps.md
Webhooks	Callback events, payload format, handler examples	webhooks.md
Embedding	iFrame, Widget, LiveKit integration + avatar IDs	embedding.md
Providers/Avatars	Available LLMs, STT, TTS, avatars, languages, BYO-LLM	providers-avatars-languages.md
Prompting	Voice prompt strategies, guardrails, use case examples	prompting-and-use-cases.md

Conversations

Retrieve transcripts for completed sessions:

GET /v1/ext/conversation/{id} — Returns agent_id, status, transcript array, recording_url.

Workflow Guide

Determine what the user needs, then load the appropriate reference:

Task	Reference File
Creating/managing agents	agents.md
Attaching data/documents	knowledge-base.md
Reusing personas across agents	templates.md
Calling external APIs from agent	tools-and-mcps.md
Reacting to conversation events	webhooks.md
Embedding agent in website	embedding.md
Choosing LLM/voice/language	providers-avatars-languages.md
Writing effective prompts	prompting-and-use-cases.md

Developer Resources

Resource	Link
Documentation	docs.trugen.ai
API Reference	docs.trugen.ai/api-reference
Developer Portal	app.trugen.ai
Community Discord	discord.gg/4dqc8A66FJ
Support	[e-mail]
GitHub Examples	trugenai/trugen-examples
Changelog	docs.trugen.ai/changelog