The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the infsh CLI tool to perform actions such as logging in, listing available models, and generating videos. These actions are performed using the Bash tool.
[EXTERNAL_DOWNLOADS]: Mentions the installation of the infsh CLI and other related skills using npx skills add. These resources are hosted by the vendor (inference-sh) and are required for the skill to function.
[DATA_EXFILTRATION]: The infsh login command is used to authenticate the user with the inference.sh platform, which involves transmitting credentials to the vendor's domain.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because user-supplied prompts are interpolated into the --input argument of shell commands.
Ingestion points: The prompt field within the JSON input for infsh app run commands.
Boundary markers: The prompt is encapsulated within a JSON string and single-quoted shell arguments.
Capability inventory: The skill is authorized to use Bash to run infsh commands.
Sanitization: The skill does not explicitly define sanitization or escaping logic for the user-provided prompt text.

google-veo