ai-visibility-audit

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow ingests free text only from a specific public website it actively crawls via curl (robots.txt and representative $URL HTML) at steps 7-10 of SKILL.md / references/checks.md, so an outsider who can author that site content could inject poison into the crawled page text.