brand-persona-skill

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1A "Brand Soul Distillation" explicitly instructs the agent to ingest brand materials including website copy, social media archives (X/Instagram), chat exports and other public content (and Phase 1B even suggests using WebSearch for competitor references), which are untrusted/user-generated third‑party sources that the agent is expected to read and that will directly shape persona.json, trigger mappings, and execution decisions.