video-prompting-guide

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructions include a command to install the vendor's command-line interface by piping a remote script to the shell (curl -fsSL https://cli.inference.sh | sh). This is documented as an installation procedure for the 'infsh' tool required by the skill.
  • [EXTERNAL_DOWNLOADS]: The guide references and downloads binaries from vendor-controlled subdomains such as dist.inference.sh and cli.inference.sh for tool installation and verification.
  • [COMMAND_EXECUTION]: The skill is configured to use the Bash tool to execute infsh commands, which is consistent with its primary purpose of running video generation applications.
  • [DATA_EXFILTRATION]: No unauthorized network operations or sensitive file access patterns were detected. Network activity is limited to the vendor's official API and documentation sites.
  • [PROMPT_INJECTION]: The content consists of educational material and prompt templates; it contains no instructions designed to bypass agent safety filters or override system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:54 AM