skills/adobe/skills/stardust/Gen Agent Trust Hub

stardust

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts for loading context and performing workspace audits, as well as utilizing npx for external tools. These operations are within the scope of the skill's documented functionality.- [EXTERNAL_DOWNLOADS]: Stardust requires an external dependency, 'impeccable', which users are directed to install from a public GitHub repository. This is a standard requirement for this design tool chain.- [PROMPT_INJECTION]: The skill ingests untrusted data from external websites to inform the redesign process, creating a potential surface for indirect prompt injection. Ingestion points: crawled site content in 'stardust/current/pages/'. Boundary markers: provenance blocks in generated artifacts. Capabilities: file system operations and script execution. Sanitization: content is parsed into structured JSON models before use.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:20 AM