The Agent Skills Directory

[SAFE]: No security issues detected. The skill content is purely informational, consisting of guidelines, best practices, and platform-specific image dimensions.
[INDIRECT_PROMPT_INJECTION]: The skill references local project configuration files (.claude/project-context.md or .cursor/project-context.md) to ensure brand consistency. While this defines a data ingestion surface for untrusted content, the skill does not have any sensitive capabilities such as network access, file writing, or command execution, rendering the risk negligible.
Ingestion points: .claude/project-context.md and .cursor/project-context.md (SKILL.md)
Boundary markers: Absent
Capability inventory: No tool usage, network operations, or command execution detected across the skill instructions.
Sanitization: Absent

visual-content