The Agent Skills Directory

[SAFE]: The skill serves as a technical integration guide for the @virtuoso.dev/message-list component. It includes clear instructions on project setup, data modeling, and UI implementation for chat applications.
[SAFE]: All identified external dependencies, such as @ngneat/falso for mock data and simplebar-react for custom scrollbars, are well-established libraries in the developer community.
[SAFE]: The licensing mechanism described is a standard commercial practice. It uses a local validation process via the VirtuosoMessageListLicense component, which does not involve network requests for key verification.
[INDIRECT_PROMPT_INJECTION]: As a UI library for chat interfaces, the component naturally renders data that could contain untrusted input. However, the skill provides no capabilities for the agent to execute code or perform sensitive operations based on this data, making the attack surface non-exploitable at the skill level.
Ingestion points: The data prop of the VirtuosoMessageList component (found in SKILL.md and various tutorial files).
Boundary markers: Not applicable as the skill is a display-oriented library.
Capability inventory: The skill is restricted to UI rendering and scroll management; it lacks file system, shell, or network capabilities.
Sanitization: The documentation focuses on rendering logic; content sanitization is expected to be handled by the consuming application.

message-list