The Agent Skills Directory

[SAFE]: The skill is entirely instructional and operates as a text-generation prompt for lesson planning. It does not include any scripts, shell commands, or network-enabled tools.
[PROMPT_INJECTION]: The skill implements an indirect prompt injection surface by interpolating user-provided inputs directly into the system prompt without using boundary markers.
Ingestion points: Fields such as local_ecosystem and curriculum_objective in the SKILL.md prompt section.
Boundary markers: Absent; variables are not enclosed in delimiters like triple quotes or XML tags.
Capability inventory: The skill does not explicitly call tools, but its configuration does not restrict the model's access to available platform tools.
Sanitization: No validation or escaping is performed on the user-supplied strings before interpolation.

ecological-inquiry-anchor-designer