The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill documents an installation command curl -fsSL https://superset.sh/cli/install.sh | sh which fetches and executes a shell script directly from the vendor's official domain superset.sh to install the required CLI tool.
[COMMAND_EXECUTION]: The skill utilizes the superset CLI to perform various operations, including the ability to run arbitrary shell commands within workspaces via the --command flag in superset workspaces create and superset terminals create.
[PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it ingests untrusted data from external files and command-line arguments to drive agent behavior.
Ingestion points: Data enters the context via the --prompt-file and --prompt arguments in SKILL.md (e.g., in automations create and agents create commands).
Boundary markers: The instructions do not define specific delimiters or boundary markers to separate system instructions from the embedded prompt content.
Capability inventory: The CLI is capable of spawning new agents, running terminal commands, and managing remote hosts.
Sanitization: There is no mention of sanitization or validation performed on the ingested prompt content.

superset