lead-research-assistant

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly requires "Web search access" and in the Instructions (step 3: "Research and Identify Leads") directs the agent to search and interpret public sources—e.g., job postings, GitHub repos, LinkedIn profiles, and recent news—to score leads and craft outreach, which clearly ingests untrusted, user-generated third-party content that can influence agent actions.