ai-voice-cloning
Fail
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Unverifiable Dependencies & Remote Code Execution] (CRITICAL): The skill provides instructions to run
curl -fsSL https://cli.inference.sh | sh. This is a critical security risk as it downloads and executes code from an untrusted external domain directly in the shell. - [Unverifiable Dependencies & Remote Code Execution] (MEDIUM): The skill uses
npx skills addto install components from theinference-sh/skillsrepository, which is not in the trusted scope. - [Unverifiable Dependencies & Remote Code Execution] (MEDIUM): The skill requires the
Bashtool to interact with theinfshCLI. Because the CLI is installed through an insecure method, all subsequent tool usage occurs in a potentially compromised environment. - [Indirect Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection through its text processing capabilities. Ingestion points: Text fields in voice generation payloads. Boundary markers: None. Capability inventory: Execution of shell commands via
Bash. Sanitization: No escaping or validation of external input is performed.
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