Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

ai-video-gen

skill · heygen-com/skillsMIT licenceAudited 23 Oct 2026 · source 120179e38ba5

★ 512pushed 100 days agoversion 3.2.0 # x-release-please-version
!CAUTIONGrade B · 89/100 · 10 findings · 120179e
512repo stars · whole heygen-com/skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 120179e38ba5 and observed network access and no hard-coded secrets. The audit raised 10 findings, 0 critical or high. What it does: Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “ai-video-gen (heygen-com/skills)”. Retrieved 23 Oct 2026. https://modelsatlas.com/skills/heygen-com/ai-video-gen

Trust audit

Audit 0.4.1 · source read 23 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high1 medium9 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared1 observation
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS3
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesWARN7
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (10)

MEDIUMPrompt injectionprompt.conditional_escalation · heygen-video/SKILL.md:150
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**Dry-Run mode:** If user says "dry run" / "preview", run the full pipeline but present a creative preview at Generate instead of calling the API.
Why
No further detail recorded for this rule.
Fix
—
LOWInventory / provenanceinv.hidden_file · .app.json
F-13 Inventory / provenanceCWE-1104Layer L0
.app.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · .clawhubignore
F-13 Inventory / provenanceCWE-1104Layer L0
.clawhubignore
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInventory / provenanceinv.hidden_file · .release-please-manifest.json
F-13 Inventory / provenanceCWE-1104Layer L0
.release-please-manifest.json
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWPrompt injectionprompt.fetch_and_trust · README.md:17
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Read https://raw.githubusercontent.com/heygen-com/skills/master/INSTALL_FOR_AGENTS.md and follow it.
Why
remote text is to be obeyed as instructions
Fix
—
LOWSupply chainprompt.pipe_to_shell · CLAUDE.md:110
F-08 Supply chainCWE-829 · CWE-1357Layer L2
- Install: `curl -fsSL https://static.heygen.ai/cli/install.sh | bash`
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · INSTALL.md:83
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl -fsSL https://static.heygen.ai/cli/install.sh | bash
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · INSTALL.md:97
F-08 Supply chainCWE-829 · CWE-1357Layer L2
> Install the HeyGen Skills from https://github.com/heygen-com/skills.git — clone it into your skills directory (find it with your config or ask if unsure). Install the HeyGen CLI via `curl -fsSL http
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · INSTALL_FOR_AGENTS.md:155
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl -fsSL https://static.heygen.ai/cli/install.sh | bash
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainprompt.pipe_to_shell · README.md:76
F-08 Supply chainCWE-829 · CWE-1357Layer L2
curl -fsSL https://static.heygen.ai/cli/install.sh | bash
Why
No further detail recorded for this rule.
Fix
—

Audit 0.4.1 · source sha 120179e38ba5 · 23 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherheygen-com GitHub organizationOwner of the repository this skill is read from
  • Source folderheygen-com/skillsThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict120179e38ba5A new audit runs when the source changes
  • Repository statusNot archivedLast push 100 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Create a persistent HeyGen avatar — a reusable face + voice identity for the agent, the user, or any named character — powered by HeyGen Avatar V technology. Prompt-based creation by default (description → HeyGen builds…

---
version: 3.2.0 # x-release-please-version
name: heygen-avatar
description: |
  Create a persistent HeyGen avatar — a reusable face + voice identity for the agent,
  the user, or any named character — powered by HeyGen Avatar V technology.
  Prompt-based creation by default (description → HeyGen builds it); photo upload is
  optional for real-person digital twins.
  Use when: (1) giving the agent a face + voice so it can present videos
  ("bring yourself to life", "create your avatar", "give yourself an avatar",
  "design a presenter", "set up an avatar", "let's make an avatar"),
  (2) the user wants to appear in videos as themselves ("create my avatar",
  "I want my face in a video", "digital twin of me", "build me an avatar"),
  (3) building a named character presenter ("create an avatar called Cleo",
  "design a character named X"), (4) establishing HeyGen identity before making videos —
  the correct FIRST step when no avatar exists yet.
  Chain signal: when the user says both an identity/avatar action AND a video action in the same
  request ("create an avatar AND make a video", "set up identity THEN create a video",
  "design a presenter AND immediately record"), run heygen-avatar first, then heygen-video.
  Returns avatar_id + voice_id — pass directly to heygen-video to create HeyGen videos.
  NOT for: generating videos (use heygen-video), translating videos, or TTS-only tasks.
argument-hint: "[name_or_description]"
allowed-tools: Bash, WebFetch, Read, Write, mcp__heygen__*
---

# HeyGen Avatar Designer

Create and manage HeyGen avatars for anyone: the agent, the user, or named characters. Handles identity extraction, avatar generation, voice selection, and saves everything to `AVATAR-<NAME>.md` for consistent reuse.

## Files & Paths

This skill reads and writes the following. No other files are accessed without explicit user instruction.

| Operation | Path | Purpose |
|-----------|------|---------|
| Read | `SOUL.md`, `IDENTITY.md` | Extract identity details when creating an avatar for the agent |
| Read | `AVATAR-<NAME>.md` | Load existing avatar identity (for variant looks, voice updates) |
| Write | `AVATAR-<NAME>.md` | Save new avatar identity after creation |
| Write | `AVATAR-AGENT.md`, `AVATAR-USER.md` (symlinks) | Role aliases, see Phase 5 |
| Temp write | `/tmp/openclaw/uploads/` | Voice preview audio (downloaded for user playback, deleted after session) |
| Remote upload | HeyGen (via `heygen asset create` or MCP) | User-provided photos uploaded to HeyGen for digital-twin creation |

Assets are only uploaded to HeyGen when the user explicitly provides them.

## Language Awareness

**Detect the user's language from their first message.** Store as `user_language` (e.g., `en`, `ja`, `es`, `ko`, `zh`, `fr`, `de`, `pt`).

1. **Communicate with the user in their language.** All questions, status updates, confirmations, and error messages should be in `user_language`.
2. **Voice design prompts and selection respect `user_language`.** When designing or selecting a voice, specify the target language so the voice library returns matches that speak it.
3. **Technical directives stay in English** — enum values (`Young Adult`, `Realistic`, `landscape`, etc.) are API-level and not translated.

## UX Rules

1. **Be concise.** No avatar IDs, group IDs, or raw API payloads in chat. Report the result (avatar created, ready to use) not the plumbing.
2. **No internal jargon.** Never mention internal phase names ("Phase 0", "Phase 5 Symlink Maintenance") to the user. The user sees natural conversation: "Setting up your avatar\u2026" not "Running Phase 2 avatar creation."
3. **One or two questions per phase.** Don't batch-ask. Walk phases in order, ask the smallest set of questions needed to proceed.
4. **Read workspace files before asking.** `SOUL.md`, `IDENTITY.md`, `AVATAR-*.md` at the workspace root contain identity. Check them first. Only ask the user for what's genuinely missing.
5. **Don't narrate skill internals.** Never say "let me read the workflow," "checking the reference files," "loading the avatar discovery guide." Read silently. The user sees questions and results, not internal navigation.
6. **Don't announce what you're about to do.** Skip meta-commentary like "Creating the avatar now." Just do the work. If a step takes time, the next thing the user hears should be the result (or a checkpoint question).
7. **Never narrate transport choice.** MCP vs CLI is internal. Pick the transport silently and never mention it. If both are unavailable, ask the user to configure one without explaining why.

## Start Here (Critical)

**Default target = the agent.** The primary use of this skill is giving the agent a face + voice so it can present videos. Route to "user" only on explicit "my avatar" / "me" / "my photo" language. When in doubt, make the agent's avatar.

**Do NOT batch-ask questions.** No "give me a photo, voice preference, duration, target platform, tone, key message" all at once. Walk phases in order. Each phase asks at most one or two things at a time.

**For agent avatars: read SOUL.md and IDENTITY.md first, then go straight to prompt-based creation.** Do NOT ask the user for a photo or appearance details first. The agent's identity lives in those workspace files. Only ask the user for traits that are genuinely missing.

**Prompt-based is the default creation path.** Photo is opt-in, only relevant when the user explicitly wants a real-person digital twin of themselves. Agents and named characters almost always use prompt-based creation.

## Before You Start (environment detection)

Try to read `SOUL.md` from the workspace root.

- **Found** → OpenClaw environment. Skip this entire section and go straight to Phase 0. Workspace-native identity (SOUL.md, IDENTITY.md) will drive agent onboarding.
- **Not found** → Claude Code environment, no workspace identity files. Still go to Phase 0 next — do NOT skip ahead to listing user avatars or asking the user for a photo.

**⚠️ 

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 120179e

Download folder ↗
git clone https://github.com/heygen-com/skills.git ~/.openclaw/skills/heygen-skills
git clone https://github.com/heygen-com/skills.git ~/.claude/skills/heygen-skills
git clone --single-branch --depth 1 \
git clone --single-branch --depth 1 https://github.com/heygen-com/skills.git <install-path>/heygen-skills
claude mcp add --transport http heygen https://mcp.heygen.com/mcp/v1/

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 120179e38ba5 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
Claude DesktopMentioned in its text, not testedSkills for Claude Desktop · About Claude Desktop
CodexMentioned in its text, not testedSkills for Codex · About Codex
GitHub CopilotMentioned in its text, not testedSkills for GitHub Copilot · About GitHub Copilot
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
Gemini CLIMentioned in its text, not testedSkills for Gemini CLI · About Gemini CLI
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 120179e38ba5

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/heygen-com/ai-video-gen/badge.svg)](https://modelsatlas.com/skills/heygen-com/ai-video-gen/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

guizang-ppt-skill✓SAFE

op7418/guizang-ppt-skill

生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、演讲者视图、观众屏同步、讲稿备注、章节幕封、数据大字报、图片网格等模板。提供两种风格:1 "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) 2 "瑞士国际主义"(无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮)。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss…

★ 28kGrade B
anysearch!CAUTION

anysearch-ai/anysearch-skill

Real-time search engine supporting web search, vertical domain search, parallel batch search, and URL content extraction.

★ 6.7kGrade B
Browserstack✓SAFE

LeoYeAI/openclaw-master-skills

Run tests on BrowserStack. Use when user mentions "browserstack", "cross-browser", "cloud testing", "browser matrix", "test on safari", "test on firefox", or "browser compatibility".

★ 2.2kGrade B
Coverage✓SAFE

LeoYeAI/openclaw-master-skills

Analyze test coverage gaps. Use when user says "test coverage", "what's not tested", "coverage gaps", "missing tests", "coverage report", or "what needs testing".

★ 2.2kGrade B
Generate✓SAFE

LeoYeAI/openclaw-master-skills

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".

★ 2.2kGrade B
Init✓SAFE

LeoYeAI/openclaw-master-skills

Set up Playwright in a project. Use when user says "set up playwright", "add e2e tests", "configure playwright", "testing setup", "init playwright", or "add test infrastructure".

★ 2.2kGrade B

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/heygen-com/ai-video-gen/badge.svg)](https://modelsatlas.com/skills/heygen-com/ai-video-gen/)

Questions about ai-video-gen

What does the ai-video-gen skill do?
HeyGen AI agent skills — avatar creation and video production via the v3 Video Agent pipeline
Is ai-video-gen safe to install?
With care. The audit graded it B (89/100) and found 10 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can ai-video-gen access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does ai-video-gen work with?
Its documentation mentions claude-code, claude-desktop, codex, copilot, cursor, gemini-cli and openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (120179e38ba5), read on 2026-10-23. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.