The Agent Skills Directory

[SAFE]: The skill instructions are purely functional and focused on UX design methodology. No malicious code, obfuscation, or unauthorized data exfiltration patterns were identified.- [DATA_EXPOSURE]: The skill manages project data by reading from design-evaluation.md and writing to .sage/work//design-brief.md. These operations are restricted to the local workspace and align with the expected behavior of a development-oriented AI agent skill.- [PROMPT_INJECTION]: The skill handles data from an external evaluation file. Although this presents a surface for indirect prompt injection, the risk is mitigated by the structured interaction model where the agent is instructed to confirm all significant design directions with the user before finalizing the brief.

ux-brief