Color Palette Generator

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The skill is designed to ingest and process data from external, untrusted sources which can be leveraged for indirect prompt injection attacks.
  • Ingestion points: Workflow 3 (Palette from Inspiration) accepts external URLs ('Competitor site') and images ('Image/photo reference').
  • Boundary markers: There are no defined boundary markers or delimiters specified to separate external content from the agent's internal instructions.
  • Capability inventory: The skill explicitly integrates with tools capable of external interaction, specifically Firecrawl for web crawling and Playwright for browser automation.
  • Sanitization: There is no evidence of sanitization or filtering logic for content retrieved from external sites before it is interpolated into the agent's reasoning process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 07:33 AM