alterlab-vcd-color-theorist

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to "Search the web" and "Research first" for color trends and cultural associations (see Workflow → Context & Research and Agentic Protocol), requiring it to fetch and ingest public third‑party web content that can materially influence palette decisions and subsequent actions, so it exposes the agent to untrusted external content.