The Agent Skills Directory

[SAFE]: The skill operates entirely through natural language instructions and logical routing rules. No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected.
[DATA_EXPOSURE]: The skill references a shared design state and an external reference file (../design-tree-core/REFERENCE.md), which are standard practices for maintaining context across a multi-skill workflow. No access to sensitive system files or credentials was found.
[REMOTE_CODE_EXECUTION]: There are no package dependencies (Python or Node.js) or remote script download patterns in the skill files.

design-orchestrator