The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior during the design and code generation phases.
Ingestion points: Reads external design briefs, brand assets, and relevant source files (SKILL.md Section 1). It also retrieves reference images from external URLs and files (references/board-standard.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these external sources.
Capability inventory: The skill has the capability to write files to the project directory (docs/visual-direction.md in SKILL.md Section 5) and generates functional HTML, CSS, and SVG prototypes (references/rich-preview.md).
Sanitization: There are no explicit instructions for sanitizing or escaping content from external references before it is interpolated into prompts or generated as code.

visual-exploration