ai-visibility-audit

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

• Third-party content exposure detected (high risk: 0.85). The workflow’s runtime path calls unifapi endpoints like geo/serp and browser/markdown, which ingest readable public web content (e.g., SERP result pages / winning cited pages) authored by third parties, and that free text is then placed into the agent’s LLM context for analysis.