ux-flow

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of instructional text that guides the agent through UX design principles and document-based information architecture. It does not include scripts, shell commands, or network requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading local project files to gather context, which is a standard ingestion surface.
  • Ingestion points: The skill reads local files such as CLAUDE.md, DESIGN-LANGUAGE.md, and the components/patterns/ directory to understand the project environment.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the referenced files.
  • Capability inventory: The skill is used to generate design documentation, ASCII diagrams, and structural code templates. It references an external command /ss-page but does not possess internal capabilities for direct system manipulation or network access.
  • Sanitization: No specific sanitization or validation logic is defined for the content of the referenced documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:32 PM
Security Audit — agent-trust-hub — ux-flow