personal-brand

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly requires ingesting and acting on public third-party content — e.g., Capability E "Brand Refresh" asks for access to the user's current online presence (LinkedIn, personal site, recent talks or posts) and references/audience-channel-map.md directs running WebSearch queries (site:linkedin.com, Substack, podcast guest searches) so the agent would fetch and interpret arbitrary public web or social content as part of its decisions.