The Agent Skills Directory

[CREDENTIALS_SAFE]: The skill implements robust security measures for API key management. It provides clear instructions for users to store their API key in an environment variable (APIMODELS_API_KEY) or a dedicated configuration file with restricted permissions (~/.apimodels/credentials with mode 0600). The scripts/generate.mjs script specifically prevents keys from being passed as command-line arguments (avoiding process listing leaks) and ensures keys are never echoed back in the terminal or chat history.
[COMMAND_EXECUTION]: The skill uses Node.js scripts to perform its primary functions. These scripts are self-contained and used for API communication, authentication, and output processing. Command execution is limited to these provided scripts using well-defined arguments.
[EXTERNAL_DOWNLOADS]: The skill communicates with api.apimodels.app for its core functionality and raw.githubusercontent.com (implicit in build processes) for model catalog updates. These are established service endpoints necessary for the skill's operation.
[DATA_EXFILTRATION]: There are no patterns suggesting unauthorized data exfiltration. The skill requires an API key for its intended purpose and communicates solely with its own official API endpoints to process image generation requests.
[PROMPT_INJECTION]: The skill contains instructional content and rules for the agent, but no malicious override patterns or safety bypasses were detected. The rules are focused on maintaining platform consistency and accurate pricing information.

apimodels-image