The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a shell script (scripts/omada-api.sh) to perform API calls using curl and jq. The script uses the -k (insecure) flag in curl, which bypasses SSL certificate verification and is considered an insecure practice.
[EXTERNAL_DOWNLOADS]: The script performs network requests to a user-defined external Omada Controller URL to fetch data and manage the network environment. This is the intended primary purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes JSON data returned from the network controller's API. This presents a potential attack surface where malicious metadata stored on the controller (e.g., client or device names) could attempt to influence the agent's logic.
[SAFE]: External references point to official TP-Link domains and well-known community resources. Credentials are managed via standard local environment files, adhering to safe secret management practices.

omada-controller