Back to skill

Security audit

Huo15 HeyGen Digital Avatar

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent HeyGen video-generation skill, but users should be aware it uses local API credentials and sends scripts to HeyGen, which may incur costs.

Install only if you intend to use HeyGen from OpenClaw. Review prompts before generation because the script text is sent to HeyGen and API calls may be billed. Keep the local heygen_creds.json file protected and avoid including secrets, regulated data, or confidential material in generated scripts unless that use is approved.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are broad enough to match common requests about video creation, which can cause the skill to activate unexpectedly. In a skill that reads local credentials and sends user content to an external API, over-broad activation increases the chance of unintended third-party data transmission and unintended billing activity.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
AVATAR_ID = creds['avatar_id']
API_KEY = creds['api_key']
BASE_URL = 'https://api.heygen.com/v1'

HEADERS = {
    'Authorization': f'Bearer {API_KEY}',

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The examples accept arbitrary script text and submit it to HeyGen's external API, but the skill description does not clearly disclose this data flow. Users may provide sensitive or proprietary content believing it stays local, leading to privacy, confidentiality, and compliance risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This code sends user-provided script content along with authentication credentials to an external HeyGen endpoint. External transmission is expected for the feature, but it is still security-relevant because sensitive user content may be exfiltrated to a third party and API usage may incur costs if triggered unintentionally.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
if voice_id:
        payload['video']['script']['voice_id'] = voice_id
    
    response = requests.post(url, headers=HEADERS, json=payload)
    return response.json()

# 使用示例

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language instructions, examples, and labels are entirely Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally region-specific. This can violate language or locale policy where skills should not force a single language without user choice or justification.

Content

No source excerpt is available for this finding.