voice-dossier-builder

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required runtime workflow for “voice-dossier-builder” ingests outsider-provided free text by collecting the user’s own posts/emails/deck exports (and possibly keyless pulls) as an untrusted corpus to extract traits, including via pasted/exported content the user supplies into the skill’s collection step.