drift

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly exposes Drift conversation and message endpoints (e.g., "get-conversation-messages", "list-conversations" and the Membrane proxy request flow) which ingest untrusted, user-generated chat content that the agent is expected to read and can influence subsequent actions, allowing indirect prompt injection.