web-scraping
Fail
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Use of homoglyph characters in code identifiers. The class definition
TrafilaturaСscraperand its subsequent instantiation in theScrapingCascadeclass utilize a Cyrillic 'С' (U+0421) instead of the Latin 'C' (U+0043). This technique is commonly used to evade text-based security filters and signature detection. - [EXTERNAL_DOWNLOADS]: The skill utilizes several well-known third-party libraries for web scraping and automation, including
requests,trafilatura,beautifulsoup4,playwright,playwright-stealth,yt-dlp,instaloader, andfake-useragent. These are standard tools for data extraction. - [PROMPT_INJECTION]: Potential surface for indirect prompt injection due to processing untrusted data from external websites.
- Ingestion points: The skill fetches content from arbitrary URLs through multiple scraping classes (e.g.,
TrafilaturaСscraper.fetchandRequestsScraper.fetch). - Boundary markers: The instructions do not implement explicit delimiters or boundary markers to separate scraped content from the agent's instructions.
- Capability inventory: The skill includes capabilities for network operations (
requests.get,playwright.goto) and file system writes (yt_dlpfor video downloads,instaloaderfor media). - Sanitization: The
RequestsScraperclass uses BeautifulSoup to remove potentially dangerous elements likescriptandstyle, and thetrafilaturalibrary provides high-quality text extraction that filters out non-content elements.
Recommendations
- AI detected serious security threats
Audit Metadata