find-marketing-agency

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

• Third-party content exposure detected (medium risk: 0.30). The workflow queries an external professional services catalog API (ServiceGraph), where agency profiles, descriptions, and metadata returned in search results and unlocks are authored by third parties and ingested by the agent.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to make REST API calls and use an MCP server provided by servicegraph.co, which is a recognized third-party service and publisher provenance.