llm-mention-tracking

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads live AI search engine answers and mention data via UnifAPI (geo/* endpoints) to track brand and competitor mentions across public prompts, which can contain outsider-authored text/content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external MCP server URL (https://mcp.unifapi.com) and a package installation command (npx skills add unifapi-agent/agents) used to configure operational data retrieval, which constitutes a common/reputable unofficial operational dependency.