ai-video-generation
Fail
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill contains an instruction to download a script from a remote URL and pipe it directly to a shell for execution. This 'curl pipe sh' pattern allows for the execution of arbitrary code from an external server without verification or auditing. Evidence: 'curl -fsSL https://cli.inference.sh | sh' in SKILL.md.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute CLI commands for video generation tasks, relying on a tool installed via an insecure remote script.
- [PROMPT_INJECTION]: The skill processes untrusted external data (URLs) as inputs to shell commands, creating a surface for indirect prompt injection. Ingestion points: image_url, audio_url, and video_url parameters in SKILL.md. Boundary markers: No delimiters or warnings are used to separate untrusted data. Capability inventory: Command execution via Bash tool for multiple application models. Sanitization: No sanitization or validation of the input URLs is present.
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