Skills
Navigate
skills/francostino/opencode-skills-collection/design-md/Gen Agent Trust Hub

design-md

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses web_fetch or read_url_content to download HTML source code and visual assets from URLs provided dynamically by the Stitch platform tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, specifically HTML and CSS from Stitch projects, to extract design tokens.
  • Ingestion points: HTML source code from htmlCode.downloadUrl and project metadata from get_project and get_screen tools.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed HTML content.
  • Capability inventory: The agent uses web_fetch and read_url_content for data retrieval and performs file-write operations to create DESIGN.md files.
  • Sanitization: No explicit sanitization or filtering of the retrieved HTML content is specified before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 04:57 PM