configure

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks the user for a webhook endpoint and then embeds that value verbatim into CLI commands and saved config (e.g., npm run generate:http-hooks -- <webhook-url> and saveConfig({ webhookUrl: "<webhook-url>" })), which requires the agent to handle/output user-provided secret-like values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly enables MCPs that fetch and ingest public web content (notably the Tavily MCP described in "Step 5: Configure MCPs" and references/mcp-config.md, which provides tavily_search/tavily_extract/tavily_crawl used by agents like web-research-analyst and market-intelligence), so the agent is expected to read untrusted, user-generated third‑party web content that can materially influence agent decisions and tool use.