web-archive-scraper

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

• Third-party content exposure detected (high risk: 0.95). When --fetch or --fetch-all is enabled, the script fetches archived HTML from web.archive.org (Wayback snapshot content) and strips it to readable text via strip_html(_get(rec["raw_url"])), so outsider-authored page body text is ingested into the LLM context as the content field.