google-veo
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a link to installation instructions for the
infshCLI tool hosted on the officialinference-shGitHub repository. - [COMMAND_EXECUTION]: The skill utilizes the
infshCLI via Bash to manage user authentication, list available AI models, and trigger video generation tasks. - [PROMPT_INJECTION]: User-supplied text prompts are interpolated into shell commands for video generation. This represents an indirect prompt injection surface where untrusted data could potentially influence model behavior, though the use of JSON-structured input (
--input '{\"prompt\": \"...\"}') provides a layer of data separation.
Audit Metadata