The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute @openant-ai/cli@latest from the NPM registry. This is a verified vendor resource belonging to the skill author (openant-ai).
[COMMAND_EXECUTION]: Shell commands are used via the Bash tool to interact with the platform. The skill explicitly mitigates risk by instructing the agent to confirm with the user before performing destructive operations like teams delete or teams remove-member.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes team names and descriptions from external CLI output.
Ingestion points: Data retrieved from teams list and teams get commands in SKILL.md.
Boundary markers: None identified; output is requested in JSON format which provides structure but not instructional isolation.
Capability inventory: The agent can perform various team management actions via Bash commands.
Sanitization: No specific content filtering or sanitization of the CLI output is specified.

manage-teams