cold-outreach-sequence

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to run web_search queries ("Research tool calls — run before writing: web_search('[Company] [Founder/Name] news 2026')" and to include "Source: [URL or platform]" in the Research Summary), meaning it fetches and must interpret open/public third-party content that can change outreach decisions.