apple

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and reads pages on apple.com, which is a third-party public website where arbitrary content fetched at runtime constitutes low-risk indirect prompt injection.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to connect a remote MCP server via HTTP from unbrowse.ai, which acts as a third-party unofficial intermediary supplying operational tools and behavior, resulting in a medium provenance tier.