outbound-prospecting-engine

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run signal-detection on public/untrusted sources (e.g., "LinkedIn posts/comments" in the "Define Signal Sources" table and job postings/funding announcements) and to ingest that signal context to drive personalization and campaign actions, meaning user-generated third-party content is read and can materially influence agent decisions.