flipsnack

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

• Third-party content exposure detected (low risk: 0.10). The agent reads templates and pages from flipsnack.com, which is a public website where content can be authored by third parties, representing an indirect prompt injection risk via search results and page reading.

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 remote third-party MCP server hosted on unbrowse.ai, which provides executable tool definitions and remote API calls that govern the agent's behavior at runtime, representing a common/reputable unofficial operational dependency.