glmv-web-replication

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 open and recursively explore a user-supplied target URL with agent-browser or Playwright (e.g., "agent-browser open ", interaction and asset-download steps, and recording external links like https://www.angelokeirsebilck.be/), thereby ingesting untrusted public website content which the agent must interpret and act on to drive navigation and replication.