llm-citation-monitor

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

• Third-party content exposure detected (low risk: 0.10). The skill’s workflow records and reports citation evidence based on user-defined target pages and approved observation modes, but it does not specify any runtime ingestion of outsider-authored free text without first selecting specific items (e.g., only “public fetch” is listed as an approved mode, not an always-on monitored feed/queue/post-submission text source).