The Agent Skills Directory

[SAFE]: The skill's behavior is consistent with its stated purpose of facilitating technical planning between designers and engineers. It uses authorized tool calls for project research and ticket creation without attempting to access sensitive credentials or perform unauthorized network operations.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its ingestion of untrusted data from external design sources.
Ingestion points: The skill retrieves external content via the Figma MCP tools (get_design_context, get_screenshot) and the Read tool for screenshots.
Boundary markers: Absent. There are no instructions in SKILL.md to wrap the ingested design context in delimiters or to include guardrail instructions to ignore potential commands embedded in designs.
Capability inventory: The agent is authorized to perform codebase exploration (reading local files) and issue creation (writing to the external Linear platform).
Sanitization: Absent. The skill does not implement validation or filtering of the content retrieved from external design tools before incorporating it into the technical plan generation process.

feature-planner