webextrator

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill sends user-provided URLs to https://api.acedata.cloud/ for rendering and extraction. This is the intended core function of the skill and targets the vendor's official domain.
  • [EXTERNAL_DOWNLOADS]: The documentation references the installation of mcp-webextrator via pip. This package is an official resource provided by the author 'acedatacloud'.
  • [SAFE]: The skill follows security best practices by instructing users to manage sensitive API tokens using environment variables within a .env file rather than hardcoding them into scripts.
  • [PROMPT_INJECTION]: While the skill ingests untrusted data from arbitrary web pages (indirect injection surface), this is inherent to its purpose as a web scraper. The data is returned in a structured format, and the extraction logic is managed via the vendor's API, which mitigates direct execution risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 12:10 PM
Security Audit — agent-trust-hub — webextrator