ClawHub
Back to skill

Security audit

HeyGen AI Avatar Video (Lite)

Security checks for vulnerabilities and agentic risk

Overview

This is a simple HeyGen API guide whose network use and API key handling match its stated video-generation purpose.

Install only if you are comfortable using HeyGen as a third-party service. Treat scripts, avatar/voice choices, likeness material, and API keys as sensitive; avoid sending secrets or private content, and consider using a scoped or rotated HeyGen API key.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Credential Access

High
Category
Privilege Escalation
Content
1. **HeyGen Account** (Creator plan or above)
   - [**👉 Sign up for HeyGen**](https://www.heygen.com/?sid=rewardful&via=clawhub) — new users get 1 free video!
   - Get API key from Settings → API

2. **Custom Avatar** (optional)
   - Upload training video to create your digital twin
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: List Available Avatars

```bash
curl -X GET "https://api.heygen.com/v2/avatars" \
  -H "X-Api-Key: $HEYGEN_API_KEY" | jq '.data.avatars[:5]'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: List Available Avatars

```bash
curl -X GET "https://api.heygen.com/v2/avatars" \
  -H "X-Api-Key: $HEYGEN_API_KEY" | jq '.data.avatars[:5]'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 2: List Available Avatars

```bash
curl -X GET "https://api.heygen.com/v2/avatars" \
  -H "X-Api-Key: $HEYGEN_API_KEY" | jq '.data.avatars[:5]'
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to send API keys and user-provided text to a third-party service for avatar/video generation, but it provides no disclosure about data sharing, retention, or privacy implications. This is risky because users may submit sensitive scripts, likeness data, or account credentials without understanding that the content leaves their environment and is processed externally.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 4: Generate a Video

```bash
curl -X POST "https://api.heygen.com/v2/video/generate" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
94% confidence
Finding
The generate-video example transmits user text and authentication material to an external API, which is materially more sensitive than simple metadata lookup. Because the skill lacks any consent, privacy, or retention notice, users may unknowingly expose proprietary scripts, personal content, or cloned-voice related material.

External Transmission

Medium
Category
Data Exfiltration
Content
### Step 4: Generate a Video

```bash
curl -X POST "https://api.heygen.com/v2/video/generate" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
Confidence
94% confidence
Finding
The generate-video example transmits user text and authentication material to an external API, which is materially more sensitive than simple metadata lookup. Because the skill lacks any consent, privacy, or retention notice, users may unknowingly expose proprietary scripts, personal content, or cloned-voice related material.

Static analysis

No suspicious patterns detected.