svg-logo-maker

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and loads the svg.js library from cdn.jsdelivr.net. This is a well-known service for delivering open-source packages and is considered a safe source for development tools.
  • [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the skill collects brand information from users and embeds it into a generated HTML workspace file. This file is subsequently executed using the agent's browser tools.
  • Ingestion points: User-provided brand name, mission, and adjectives gathered in Phase 1.
  • Boundary markers: No specific delimiters or warnings are instructed to be used when inserting these values into the HTML scaffold.
  • Capability inventory: The skill utilizes browser_navigate, browser_snapshot, and browser_get_input_value to render and interact with the logo code.
  • Sanitization: The skill does not explicitly describe sanitization steps for user-supplied strings before they are written into the _logo-workspace.html file.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 10:38 PM