web-scraper

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches content from arbitrary external URLs. This creates a surface for indirect prompt injection, as malicious actors could embed hidden instructions within a website's HTML to influence the AI agent's behavior when the scraped content is processed.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes several third-party Python libraries including beautifulsoup4, requests, lxml, pandas, and click. These are well-known, industry-standard packages for web scraping and data manipulation and are considered safe sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:25 PM