web-crawler
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with external APIs including ScrapeCreators (api.scrapecreators.com), Firecrawl (api.firecrawl.dev), and Apify (api.apify.com) to perform its core functions. These are well-known services for web scraping and data extraction. The skill also retrieves snapshots from the Internet Archive (archive.org) and archive.today mirrors.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from diverse external sources like YouTube, TikTok, and news sites. It includes specific instructions for the agent to verify metadata and treat the extracted text as a substrate, reducing the risk of being misled by content embedded in the scraped data. No dangerous local capabilities are exposed to this ingested data.
- [DYNAMIC_EXECUTION]: The script
exports.pyand instructions inSKILL.mdutilize dynamic path insertion (sys.path.insert) to ensure the skill's helper functions can be imported correctly from its relative installation path. This is a common and safe pattern for modular agent skills.
Audit Metadata