The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided wireframes, prototypes, and user flows (Ingestion point: User queries). It lacks explicit boundary markers or instructions to ignore embedded commands within this data (Boundary markers: Absent). However, because the skill has no code-execution, file-write, or network capabilities (Capability inventory: Display and internal reasoning only), and no sanitization is present (Sanitization: Absent), the risk is categorized as low since it can only influence the agent's textual output or reasoning.
[Remote Code Execution] (SAFE): No remote code patterns or script downloads were identified.
[Data Exfiltration] (SAFE): No network operations or sensitive file access patterns were detected.
[Prompt Injection] (SAFE): No instructions targeting the bypass of system safety filters or the extraction of system prompts were found.

ux-designer-assistant