The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use curl commands to interact with the EachLabs API. This is the intended primary function of the skill and targets the vendor's verified domain (sense.eachlabs.run).
[EXTERNAL_DOWNLOADS]: The documentation references media outputs (images/videos) generated by the API and hosted on the vendor's official storage domain (storage.eachlabs.ai). These are standard assets produced by the service during normal operation.
[CREDENTIALS_UNSAFE]: Security best practices are followed by using the $EACHLABS_API_KEY environment variable placeholder for authentication, ensuring no sensitive credentials are hardcoded in the skill instructions.
[DATA_EXFILTRATION]: User-provided presentation topics and content requirements are transmitted to the EachLabs API for processing. This data flow is necessary for the skill's core functionality and occurs over an encrypted connection to the official vendor endpoint.
[PROMPT_INJECTION]: The skill manages user input through structured JSON payloads sent to a remote API. While it processes untrusted user data, it does so within the context of a specialized generation task, and there are no instructions present that attempt to bypass the underlying agent's safety guardrails.

presentation-generation