ClawHub
Back to skill

Security audit

Talking Avatar

Security checks for vulnerabilities and agentic risk

Overview

The skill transparently creates talking-avatar and re-voiced videos, but it lacks consent and misuse safeguards for real people’s faces, voices, and footage.

Review before installing if you may use real people’s images, voices, or videos. Only use this skill with media you have rights and consent to use, avoid impersonation or misleading endorsements, and be aware that generated requests can send biometric likeness and voice material to external video-generation providers.

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
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill enables uploading portraits, voice audio, and existing footage of real people for lip-syncing and re-voicing, but it provides no warning or gating around consent, privacy, impersonation, or rights to use biometric/voice likeness data. In this context, the omission is security-relevant because the skill directly facilitates potentially deceptive or unauthorized synthetic media creation, increasing risk of privacy violations, impersonation, and misuse.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.