The Agent Skills Directory

[SAFE]: The skill serves as an API guide for the @helios-project/core library. All documented methods and examples involve standard web development practices for video rendering and animation. There is no evidence of credential exfiltration, malicious command execution, or unauthorized network activity.
[INDIRECT_PROMPT_INJECTION]: The skill includes utilities like createSystemPrompt and inputProps which can ingest external data into an agent's context. While this represents a theoretical attack surface for indirect prompt injection, the skill specifically provides a schema validation system to enforce data types and constraints, which acts as a security best practice for this use case. The severity is considered low as it is a documented feature of the video engine's integration with AI agents.

helios-core