ai-marketing-videos
Fail
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- REMOTE_CODE_EXECUTION (CRITICAL): The skill instructs the agent to execute a shell command that pipes a remote script directly into the system shell:
curl -fsSL https://cli.inference.sh | sh. This pattern is extremely dangerous as the content of the script can change at any time and bypasses all local security controls. - EXTERNAL_DOWNLOADS (HIGH): The skill downloads an external binary/script from
https://cli.inference.sh, which is not a pre-approved or trusted source according to the security framework. - COMMAND_EXECUTION (MEDIUM): The skill makes extensive use of the
Bashtool to executeinfshcommands and complex shell loops (for section in "${SECTIONS[@]}"; do ... done). While part of the stated purpose, this provides a large attack surface if user-controlled data is ever interpolated into these commands.
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