Back to skill

Security audit

IceCube Avatar Clone

Security checks for vulnerabilities and agentic risk

Overview

This is an informational avatar-cloning guide with expected third-party API examples, but users should handle face and voice data carefully.

Install only if you are comfortable with a guide that points users to third-party avatar and voice services. Before uploading photos, video, or voice, confirm consent from every depicted or recorded person, review each vendor's privacy and retention terms, avoid impersonation or deceptive use, and label generated media as AI-created.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to upload photos, videos, and audio to third-party avatar platforms and includes API usage, but it does not clearly disclose privacy, retention, biometric-data, and cross-border sharing risks. Because the content centers on identity media, users may submit highly sensitive personal data without informed consent or understanding of downstream use.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 78)May include surrounding context.

md
import requests

# 创建视频
response = requests.post(
    "https://api.heygen.com/v2/video/generate",
    headers={"X-Api-Key": "YOUR_API_KEY"},
    json={

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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 78)May include surrounding context.

md
import requests

# 创建视频
response = requests.post(
    "https://api.heygen.com/v2/video/generate",
    headers={"X-Api-Key": "YOUR_API_KEY"},
    json={

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 79)May include surrounding context.

md
# 创建视频
response = requests.post(
    "https://api.heygen.com/v2/video/generate",
    headers={"X-Api-Key": "YOUR_API_KEY"},
    json={
        "video_inputs": [{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill recommends combining avatar cloning with voice cloning to create a 'complete digital human' without prominently warning about impersonation, fraud, consent, and deepfake abuse risks. Pairing face and voice cloning materially increases the ability to deceive others, bypass trust signals, and create convincing non-consensual identity replicas.

Content

No source excerpt is available for this finding.