@1247/web-crawler

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the Playwright library and the Chromium browser engine as part of its setup process.
  • [COMMAND_EXECUTION]: Installation involves executing shell commands to install the browser and its system dependencies.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process content from arbitrary websites, which poses a risk of indirect prompt injection.
  • Ingestion points: The scripts/crawl.py script extracts text, metadata, and links from user-provided URLs.
  • Boundary markers: No boundary markers or delimiters are used when saving extracted content to report files like audit.md or report.json.
  • Capability inventory: The script has the ability to read from the network, interact with web pages, and write files to the local file system.
  • Sanitization: The extracted content is not sanitized or filtered before being written to the output directory.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 03:53 PM
Security Audit — agent-trust-hub — @1247/web-crawler