sec

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

• Third-party content exposure detected (low risk: 0.10). The skill searches SEC EDGAR filings via sec.gov API endpoints; while public filings may contain untrusted content, searching specific entities is an active search/fetch action rather than continuous ingestion from an uncontrolled monitored feed.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server and REST API endpoints hosted on unbrowse.ai to dynamically execute tools and fetch instructions at runtime, representing an unofficial third-party operational dependency.