linkedin-content

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill includes a command curl -fsSL https://cli.inference.sh | sh to install the inference.sh CLI. This pattern downloads a script from a remote server and executes it directly in the shell. While this is a standard distribution method for the vendor's own tools, it involves executing unverified remote code.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the infsh CLI to perform various tasks, such as running search assistants, cross-posting content, and generating images. It also uses npx to install additional related skills from the vendor's repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 02:29 PM