run-hcom-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflows and scripts explicitly ingest and act on other agents' messages and transcripts (e.g., use of "hcom events", "hcom transcript", and event-driven subscriptions in SKILL.md and the pattern scripts) and the how-it-works docs describe cross-device relay using public MQTT brokers (broker.emqx.io, broker.hivemq.com, test.mosquitto.org), so untrusted/third-party messages can be received and directly influence tool actions and orchestration.