brand-voice

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch public web content—e.g., "If Description Provided (Option B) Use WebSearch to find: Example content from admired brands, Industry voice benchmarks, Competitor voice analysis" and Option A allows providing URLs—so the agent will ingest and synthesize untrusted third‑party web content as part of its workflow.