agent-relay-orchestrator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt repeatedly shows and requires embedding a workspace API key (rk_live_...) verbatim into CLI commands (npx/agent-relay up --workspace-key), which forces the LLM to handle/output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). [The required workflow reads outsider-authored free text from Relaycast channels via mcporter call relaycast get_messages ... (and similarly DM-related endpoints), where any workspace user can post messages that the orchestrator ingests at runtime.]