The Agent Skills Directory

[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests and processes untrusted data from multiple external sources.
Ingestion points: User-provided feature descriptions, Figma design context via get_design_context, and visual content (screenshots/images) via the Read tool.
Boundary markers: The skill instructions do not explicitly require the use of delimiters or 'ignore embedded instructions' warnings when handling user or external input.
Capability inventory: The skill can read local files, access Figma designs, and create issues in Linear via MCP tools.
Sanitization: There are no instructions for validating or sanitizing the content retrieved from external visual references or user inputs before incorporating them into technical plans or Linear issues.

feature-planner