sleek-design-mobile-apps

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires the SLEEK_API_KEY environment variable for authentication, which is a standard and recommended practice for managing sensitive credentials. It also includes a specific privacy warning regarding imageUrls, noting that these are fetched by the vendor's servers and advising users to avoid sensitive content in these URLs.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for fetching SVG icon assets from the well-known Iconify API (api.iconify.design). This is a common and legitimate practice for web and mobile development workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes HTML and design data returned by the Sleek API to generate local project files.
  • Ingestion points: The skill fetches design code through the GET /api/v1/projects/:id/components/:componentId endpoint (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore previous instructions" markers are used when the agent is instructed to process or save this external content.
  • Capability inventory: The skill has the capability to write files to the local system (.html files, SVG assets) and suggests using shell commands to pipe API responses into files.
  • Sanitization: No explicit sanitization or filtering steps are defined for the HTML content before it is saved or used for native code generation.
  • [COMMAND_EXECUTION]: The skill recommends using shell commands (such as piping a curl response into a file) to efficiently save large API responses to the disk. These commands are localized to the intended purpose of managing design assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 04:33 AM