@1247/web-crawler

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

• Third-party content exposure detected (high risk: 0.90). The skill's main workflow (SKILL.md "Run --audit on the target site" and scripts/crawl.py) fetches and renders arbitrary public URLs and extracts visible text, links, console messages and clickables (see extract_text/extract_links/console capture in scripts/crawl.py), then generates audit.md and report.json that the agent is expected to read and act on, so untrusted third‑party page content could inject instructions that influence subsequent actions.