design-spec

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as user-provided images and design tool URLs (e.g., Figma) to extract requirements for visual analysis.
  • Ingestion points: Input routing occurs in Step 1 of the workflow, where the agent processes images, screenshots, and external URLs.
  • Boundary markers: The skill mandates the use of evidence tagging (SOURCED vs INFERRED) to track the origin of design claims and requires user confirmation for inferred actors or goals.
  • Capability inventory: The skill utilizes visual analysis tooling for image processing, spawn_agent for sub-task delegation, and file-system operations to save documentation in team-artifacts/ and update metadata in docs/specs/.
  • Sanitization: The instructions focus on structured output and markdown formatting but do not explicitly detail sanitization procedures for content derived from external visual inputs.
  • [SAFE]: No other security concerns were identified. The skill's file-system access and sub-agent usage are appropriately scoped to its declared purpose of generating design artifacts and maintain consistency with project documentation standards.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:11 AM