The Agent Skills Directory

[SAFE]: The skill is designed for UI/UX analysis. It processes user-provided application information and screenshots to generate structured feedback on design quality and implementation feasibility.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data via the materials input (screenshots and UI descriptions). While this constitutes an attack surface for indirect prompt injection, the skill lacks high-privilege capabilities such as file system write access, network operations, or shell execution, which minimizes the risk of a successful exploit.
Ingestion points: The materials input field in SKILL.md and skill.yaml is used to provide screenshots or descriptions of the UI being analyzed.
Boundary markers: The prompts do not explicitly define boundary markers or instructions to ignore embedded commands within the processed materials.
Capability inventory: No dangerous capabilities (network access, shell execution, or file system modifications) were found in any of the skill's scripts or prompts.
Sanitization: There is no explicit sanitization or filtering logic mentioned for the provided UI materials.

modern-uiux-review