lead-gen

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and README explicitly instruct the agent to "use web search" and to extract data from public websites, LinkedIn profiles, and recent news/funding signals—untrusted third-party content the agent must read and that is used to score leads and drive outreach actions, enabling indirect prompt injection.