prompt-discovery

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses the Promptwatch MCP server to “list_prompts”, “list_query_fanouts”, and “list_content_gap_prompts”, which at runtime will ingest free-form text originating from Promptwatch’s public/community-maintained prompt data (outsider-authored content) into the agent’s LLM context via the MCP tool responses.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires connecting at runtime to the Promptwatch MCP server (https://server.promptwatch.com/mcp), and the data fetched from that endpoint (existing prompts, fanouts, gap prompts) directly informs and controls the agent's prompt-generation and creation workflow.