creativecommons

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 from creativecommons.org, which constitutes reading general web content via search and page fetching (low risk).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures an inbound operational dependency on a remote third-party Model Context Protocol server hosted at unbrowse.ai, which provides executable tool definitions and runtime capabilities under unofficial provenance.