hansei

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 shows direct fetching of external Hansei data (e.g., "List Bot Conversations", "Send Message to Bot" and the "membrane request CONNECTION_ID /path/to/endpoint" proxy requests) which would ingest user-generated/public retrospectives and messages that the agent is expected to read and could influence subsequent actions.