available-domain-search

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

• Third-party content exposure detected (medium risk: 0.30). In the domains_check_availability and domains_suggest runtime paths, the workflow ingests the user-provided domains/query free text parameters directly to perform domain lookups and return results (including GoDaddy registration links), so outsider-authored free text is consumed without selecting any specific pre-existing item first.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill explicitly instructs runtime calls to the AgentPMT MCP/REST endpoints to fetch live schema/instructions that directly control tool behavior (e.g., https://api.agentpmt.com/mcp/ and https://api.agentpmt.com/products/purchase are used to retrieve get_schema/get_instructions at runtime), so the agent's prompts and execution depend on remote content.