spamcop

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads pages and reports from spamcop.net, which is an external domain queried by the agent via search/fetch actions (low risk).

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 at unbrowse.ai, which provides executable tool logic and behavior-governing instructions at runtime.