get-qualified-leads-from-luma

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill asks for and demonstrates using user-provided secrets (Slack webhook and API token) and shows curl/Python examples that embed/require those secret URLs/tokens, which would force the agent to handle or emit them verbatim (exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses luma-event-attendees to scrape Luma event attendee/host data (outsider-authored public web content) and then feeds that extracted free-text fields (e.g., bio/title/company) into the LLM during lead-qualification batch tasks.