The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is purely instructional and facilitates architectural design sessions without performing sensitive operations, network requests, or file system modifications.
[NO_CODE]: This skill consists entirely of markdown instructions and does not contain any executable code, scripts, or binaries, which significantly minimizes its attack surface.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted user data (module descriptions and requirements) which are interpolated into prompts for sub-agents.
Ingestion points: External descriptions and requirements provided by the user in SKILL.md.
Boundary markers: Absent; untrusted data is directly interpolated into the template.
Capability inventory: Limited to the Task tool for spawning sub-agents; no file-writing or network capabilities are invoked.
Sanitization: Absent.
Assessment: The risk is minimal as the goal is to generate architectural design variations, which do not result in executable side effects.

design-an-interface