design-exploration

Warn

Audited by Snyk on Feb 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The workflow explicitly requires "Research via Gemini" (SKILL.md
  • Investigation / Research via Gemini) to fetch web-grounded examples and trends from the open web, which the agent is expected to read and use to influence design proposals, allowing third‑party web content to materially affect subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 09:31 PM