The Agent Skills Directory

[SAFE]: The skill is composed strictly of markdown-based instructions and a reference knowledge base. No scripts, binaries, or shell commands are included or referenced.
[DATA_EXPOSURE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill's primary function is to generate design documentation.
[PROMPT_INJECTION]: The instructions provide guidance on 'Output discipline' to maintain professional formatting but do not attempt to override system safety protocols or extract system prompts.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted external data (URLs and UI descriptions) during audits. However, the risk is negligible as the skill lacks high-privilege capabilities such as file system writing or command execution.
Ingestion points: UI descriptions, screenshots, and URLs processed in 'Audit / Review' mode in SKILL.md.
Boundary markers: None identified; untrusted data is processed directly.
Capability inventory: No subprocess calls, file-write operations, or network tools are utilized in the skill files.
Sanitization: No explicit sanitization or validation of external data is performed before processing.

design