The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill recommends installing the Inference.sh CLI by piping a remote script directly to the shell (curl -fsSL https://cli.inference.sh | sh). This pattern allows for arbitrary code execution on the user system from an external source without prior verification.
[COMMAND_EXECUTION]: The skill uses the Bash tool to run the infsh command and provides multiple examples of executing shell commands to interact with the Inference.sh platform.
[EXTERNAL_DOWNLOADS]: The installation process involves downloading binary executables from dist.inference.sh. While the documentation claims the script verifies SHA-256 checksums, this verification logic itself resides in the unverified remote script.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. Ingestion points: User prompts are passed as arguments to the infsh CLI in SKILL.md. Boundary markers: No specific delimiters or instructions are used to separate user prompts from command logic. Capability inventory: The skill has access to the infsh tool via the Bash command as specified in SKILL.md. Sanitization: No input sanitization or escaping is performed on the user-provided prompt string.

google-veo