local-ai-visibility

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

• Third-party content exposure detected (low risk: 0.10). The skill’s workflow in SKILL.md describes generating town-by-engine presence and “gap” evidence using buyer-style queries, which implies the LLM ingests outsider-authored web/engine content at runtime when it records “who is named instead” and “quoted evidence” from those engines.