runway-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly includes a command "dnx Runway.Cli marketing-studio webproducts fetch --url https://example.com/product" and describes client-side OG/Twitter metadata extraction from arbitrary URLs, meaning the agent can fetch and ingest untrusted public web content that could be injected into prompts or planner inputs.