faceless-explainer

SUSPICIOUS. The skill’s capabilities largely fit its stated purpose, but it has meaningful trust and execution risk because it instructs the agent to self-update skills, install registry blocks transitively, use stored HeyGen credentials, and potentially upload project data for cloud rendering through a powerful external CLI. Data flows stay within the HyperFrames/HeyGen ecosystem rather than unrelated endpoints, so this is not confirmed malicious, but the remote update/install surface is broader than a narrowly scoped documentation skill.