skills/huangzida/skills/design-md/Gen Agent Trust Hub

design-md

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves design assets, including HTML source code and screenshots, from URLs generated by the Stitch platform. These assets are fetched using the web_fetch tool to perform technical analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external HTML and CSS files during the design analysis phase, creating a surface for potential injection attacks.
  • Ingestion points: Technical assets are downloaded via web_fetch from htmlCode.downloadUrl and screenshot.downloadUrl as described in SKILL.md.
  • Boundary markers: The instructions do not include specific delimiters or guidance for the agent to isolate the fetched content and ignore any embedded natural language instructions.
  • Capability inventory: The skill possesses Write permissions to generate DESIGN.md files and interacts with the stitch*:* toolset for project management.
  • Sanitization: There are no defined processes for sanitizing or validating the content extracted from the external HTML/CSS assets before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:20 PM