heysummit

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

• Third-party content exposure detected (high risk: 0.70). This skill's SKILL.md instructs the agent to fetch and act on HeySummit account data via Membrane (e.g., "membrane action run" and the "membrane request CONNECTION_ID /path/to/endpoint" proxy), which ingests user-generated third‑party content like talks, attendees, and event descriptions that the agent is expected to read and could materially influence subsequent actions.