cross-page-analyzer

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow described in SKILL.md is a read-only analyzer that “receives aggregated scan findings from multiple web pages,” which implies runtime ingestion of outsider-authored free text from scanned web pages (public page content/findings) into the agent’s LLM context.