Skills
Navigate
skills/redfox-data/redfox-community/gzh-search-crawler/Gen Agent Trust Hub

gzh-search-crawler

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The assets/search.py script uses subprocess.run to trigger the system open command for launching the generated HTML report. This operation uses a locally constructed URL, avoiding shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill fetches search results from redfox.hk, the official API of the skill author, which is a necessary and documented behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes article metadata from a remote API, creating an attack surface for indirect prompt injection.
  • Ingestion points: Data is retrieved from the RedFox search API by the fetch_articles function in assets/search.py.
  • Boundary markers: The skill relies on structured CSV and HTML file formats to isolate data, though terminal output lacks explicit delimiters.
  • Capability inventory: The skill can write files to the local Downloads folder and open the system's web browser.
  • Sanitization: The assets/report_template.html file includes an escapeHTML JavaScript function that sanitizes article titles and summaries before display to mitigate injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:35 AM