The Agent Skills Directory

[SAFE]: The skill demonstrates legitimate educational design functionality. All external references and shared agents (e.g., moai-core, moai-office) are consistent with the vendor's ecosystem, and no high-risk command execution or network exfiltration was detected.
[PROMPT_INJECTION]: The skill processes untrusted user-provided materials (such as existing curricula and job descriptions), which presents a standard surface for indirect prompt injection.
Ingestion points: The workflow in references/course-builder.md and references/competency-modeler.md involves reading user-supplied documents for analysis and improvement.
Boundary markers: The instructions do not specify the use of clear delimiters or instructions to the agent to ignore potentially embedded commands in user files.
Capability inventory: The skill has the ability to write files to a local _workspace/ directory and utilizes the sequentialthinking tool.
Sanitization: No specific sanitization or content validation logic is defined for the external files being processed.

curriculum-designer