oxylabs

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly exposes a "Scrape Website" action and instructs using the Membrane CLI (e.g., membrane action run) to fetch public websites via Oxylabs, returning scraped third-party content that the agent is expected to read and act on, so untrusted web content could influence subsequent decisions.