hermes-integration

SUSPICIOUS: the skill is broadly consistent with a Hermes integration, and the Hermes project provenance appears legitimate, but it grants an agent the ability to ingest untrusted cross-platform content, send messages externally, schedule recurring actions, and participate in self-modifying/dynamically generated skill loops. This is not confirmed malware, but it is a medium-risk automation/messaging integration with notable prompt-injection and autonomy concerns.