ideate

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

• Third-party content exposure detected (high risk: 0.90). This skill's workflow explicitly instructs the agent to capture and fetch external links/Figma files and to run deeper research (spawn Explore agents) against external/reference materials (see "Reference Capture" and "Act 2: Explore Approaches" in SKILL.md), meaning it ingests and acts on untrusted third-party content shared or discovered on the open web.