The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl via the Bash tool to interact with the LiteLLM proxy API. This usage is restricted to the skill's intended purpose of listing and deleting organization records.
[DATA_EXFILTRATION]: The skill manages authentication using the LITELLM_API_KEY environment variable. This follows security best practices for secret management by avoiding hardcoded credentials and utilizing standard authorization headers.
[PROMPT_INJECTION]: Indirect prompt injection is a theoretical risk when the agent processes the organization list from the API; however, the skill effectively mitigates this by requiring explicit human confirmation and review of the organization alias before executing the deletion command.

delete-org