sitemap-generator

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill identifies and uses standard Python packages including click, requests, lxml, and beautifulsoup4, as well as an MCP server package named @clawfu/mcp-skills.
  • [COMMAND_EXECUTION]: The skill provides commands for crawling websites and manipulating local files, which are executed through the main Python script provided with the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface area for indirect prompt injection because it retrieves and processes content from external URLs to generate sitemaps.
  • Ingestion points: External website content is retrieved using the requests.get() method in scripts/main.py.
  • Boundary markers: None identified to separate crawled content from the agent's internal instructions.
  • Capability inventory: The skill has the capability to perform network requests (requests.get), read local files (Path.read_text), and write to the local filesystem (ElementTree.write).
  • Sanitization: The script uses BeautifulSoup to parse HTML but does not apply specific security filters or sanitization to the extracted data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 10:11 AM