ai-avatar-video
Fail
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- Remote Code Execution (CRITICAL): The skill instructs the user and the agent to install a CLI tool using
curl -fsSL https://cli.inference.sh | sh. This method is inherently dangerous as it executes unverified code from a non-trusted domain (inference.sh) with the permissions of the current user. - External Downloads (HIGH): The skill relies on external software from
inference.sh, which is not included in the allowed list of trusted GitHub repositories or organizations. - Indirect Prompt Injection (LOW): The skill is susceptible to data-driven attacks as it processes untrusted URLs for images and audio without sanitization. Evidence: 1. Ingestion points:
image_urlandaudio_urlinSKILL.md. 2. Boundary markers: Absent. 3. Capability inventory:infshcommand execution inSKILL.md. 4. Sanitization: Absent.
Recommendations
- HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata