skyscanner

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

• Third-party content exposure detected (low risk: 0.10). The agent searches flights on Skyscanner via search tools, which ingest flight search results from an external aggregator site.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures and connects a remote Model Context Protocol (MCP) server and REST endpoints hosted at unbrowse.ai, which supplies operational tools and instructions that govern the agent's runtime behavior. Because unbrowse.ai is a third-party unofficial platform rather than an established recognized publisher or enterprise vendor, this constitutes a common/reputable unofficial operational dependency.