Skills
skills/full-statck-skills/stitch-skills/stitch-design-md/Gen Agent Trust Hub

stitch-design-md

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads design assets, such as HTML code and screenshots, from official Google Stitch domains (withgoogle.com) to perform its primary function of design system synthesis.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the processing of untrusted project data.
  • Ingestion points: Project assets (HTML and CSS) are retrieved from external URLs using the web_fetch tool as specified in SKILL.md.
  • Boundary markers: There are no instructions to the agent to treat the downloaded HTML as untrusted or to ignore any potential instructions embedded within the design code.
  • Capability inventory: The skill has access to the Write tool to create DESIGN.md and the stitch*:* toolset for interacting with Stitch projects.
  • Sanitization: The skill does not include any logic to sanitize, escape, or validate the content of the downloaded HTML before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:13 AM
Security Audit — agent-trust-hub — stitch-design-md