The Agent Skills Directory

[SAFE]: The skill integrates with official vendor endpoints (api.acedata.cloud) for face analysis and transformation tasks. These resources are owned by the skill author and represent legitimate service functionality.
[SAFE]: Credential management follows best practice by instructing users to store the API token in environment variables or a .env file, rather than hardcoding it or passing it in prompts.
[INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing external image URLs. This constitutes a data ingestion surface; however, the data is consumed by a specialized API for computer vision tasks, and there is no evidence of unsafe interpolation into agent prompts or executable contexts.
Ingestion points: User-provided image_url in all API endpoints (SKILL.md).
Boundary markers: Not specified; results are expected in structured JSON from the API.
Capability inventory: Performs network requests to api.acedata.cloud via curl commands.
Sanitization: No specific sanitization or validation of the input URLs is described in the provided documentation.

face-transform