aepd-es

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

• Third-party content exposure detected (low risk: 0.10). The required workflow searches and reads pages from aepd.es (Agencia Española de Protección de Datos) via Unbrowse MCP tools, which constitutes ingestion of external web content accessed via search or specific URLs.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to an unofficial third-party remote MCP service (unbrowse.ai) at runtime to obtain its tools and behavior, establishing a common/reputable unofficial operational dependency.