The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project timeline JSON, which serves as an ingestion point for untrusted data into the agent's context.
Ingestion points: The project argument in the start_render tool (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded content are defined for the JSON payload.
Capability inventory: The skill uses start_render to submit data to an external rendering service and get_render to track progress.
Sanitization: There are no documented sanitization or schema validation steps for the input JSON prior to processing.
[NO_CODE]: The analyzed skill consists entirely of instructional markdown and tool descriptions without any executable scripts, configuration files, or implementation code.

flowy-render