intelligent-web-scraper

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and scripts clearly fetch and ingest arbitrary public webpages (e.g., "Phase 2: Navigate to URL" with browser_navigate(url), local_browser_scraper.py examples like https://movie.douban.com/... and concurrent_scraper.py/AsyncWebCrawler calls), treat user/third‑party page content as input for analysis (pagination, detail-link following, series discovery) and use those results to decide follow-up actions and update learned patterns, so untrusted web content can materially influence the agent's behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 09:13 AM