link-prospecting

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads prospect pages, competitor backlink profiles, and third-party SERP results from web search and HarborRank tools, exposing the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external instructions and documentation at https://app.harborrank.com/mcp and https://harborrank.com/docs/mcp for operational setup and MCP server integration, constituting an unverifiable external runtime dependency under first-party HarborRank provenance.