brevo

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches and reads public web pages from brevo.com, which represents low-risk ingestion of external web content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a third-party hosted MCP server and API at unbrowse.ai to execute behavior-selecting instructions and tools, constituting a common unofficial operational dependency.