running-meetings

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested via the skill’s bundled reference materials (e.g., “12 sources, 32 insights” in references/guest-insights.md and “47 artifacts extracted from Lenny's Podcast and Newsletter” in references/artifacts.md), which are then used as the basis for the agent’s LLM context.