just-scrape

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of the just-scrape CLI tool to perform all scraping, crawling, and browser automation tasks.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install or run the just-scrape package from the npm registry using package managers like npm, pnpm, yarn, or npx.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes arbitrary content from attacker-controlled websites.
  • Ingestion points: External webpage content fetched via URLs in smart-scraper, crawl, and agentic-scraper commands.
  • Boundary markers: Uses structured flags like --schema and -p for extraction logic, but lacks explicit boundary markers to prevent the agent from following instructions embedded within the scraped data.
  • Capability inventory: The skill can perform automated browser interactions (fill forms, click, navigate) and retrieve network data.
  • Sanitization: Content processing is offloaded to the ScrapeGraph AI backend without explicit local sanitization of the scraped HTML/markdown text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 03:45 AM
Security Audit — agent-trust-hub — just-scrape