ai-avatar-video
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): The instruction to use
curl -fsSL https://cli.inference.sh | shallows for unverified code to be executed directly on the host system. This is a primary attack vector for full system compromise.\n- [EXTERNAL_DOWNLOADS] (HIGH): The skill downloads executable content frominference.sh, a domain not included in the pre-approved trusted sources list, creating a significant supply chain risk.\n- [COMMAND_EXECUTION] (MEDIUM): The skill uses theinfshCLI andnpxto fetch additional skills from the unverifiedinference-shorganization.\n- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection. Evidence: (1) Ingestion points: media URLs in SKILL.md. (2) Boundary markers: Absent. (3) Capability inventory: Subprocess calls viainfsh. (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