openclaw-bridge

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

• Third-party content exposure detected (high risk: 0.90). The skill's Session Handoff workflow (Section 5) instructs senders to "post handoff context to #comms-log" (e.g., via the Discord channel example using openclaw message send) and requires the receiving agent to "read handoff payload" and "continue from nextSteps", which means the agent ingests user-generated third‑party channel messages that can directly drive subsequent actions.