gong

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and read user-generated Gong content (e.g., "Get Call Transcripts", "Get Calls Extensive" and using "membrane request CONNECTION_ID /path/to/endpoint" proxy requests), so untrusted third‑party transcripts/library data would be ingested and could materially influence subsequent actions.