The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill body or references.
[DATA_EXPOSURE]: The skill allows the use of external image URLs and data URIs (Base64) for image-to-image and video-to-video generation. This is standard functionality for creative AI tools and does not involve exfiltration of sensitive local data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text prompts to drive image and video generation models.
Ingestion points: User-supplied prompt field in generate_image and generate_video calls (SKILL.md).
Boundary markers: None present; the prompt is passed directly to the generation tools.
Capability inventory: Submits generation requests to an MCP server and polls for status; does not have file-write or shell execution capabilities.
Sanitization: Not specified, as prompts are intended for creative generative models rather than command processing.
[COMMAND_EXECUTION]: The skill instructions include a recommendation to use crypto.randomUUID() for generating stable node identifiers, which is a standard and safe JavaScript utility for local ID generation.

studioai-generate