The Agent Skills Directory

[SAFE]: The skill operates entirely as a text-based design assistant within SKILL.md. It does not perform network operations, execute shell commands, or include external scripts. Analysis found no indicators of obfuscation, persistence, or privilege escalation.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes user-provided content.
Ingestion points: User-supplied text from fields like project_intent and curriculum_goals in SKILL.md is interpolated into the prompt.
Boundary markers: Absent; the inputs are placed directly into the prompt without protective delimiters.
Capability inventory: No dangerous capabilities (file writes, network calls, tool usage) are present in SKILL.md or the orchestrator's logic.
Sanitization: The skill does not validate or sanitize inputs for embedded instructions.

regenerative-project-design-orchestrator