geo-llms-txt

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The generate_llms_txt.py script uses the requests library to fetch content from user-provided URLs and sitemap files. This is the primary function of the tool and is used to gather metadata.
  • [COMMAND_EXECUTION]: The skill's documentation guides the user to execute local Python scripts (scripts/generate_llms_txt.py and scripts/validate_llms_txt.py) via the command line to perform website analysis and file validation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: The generate_llms_txt.py script fetches HTML content from external websites and sitemaps provided by the user.
  • Boundary markers: The script does not utilize boundary markers or explicit instructions to the AI agent to disregard embedded commands when it processes the generated llms.txt file.
  • Capability inventory: The skill uses requests.get for network access and writes the generated content to a local file. It does not perform subprocess execution or evaluate code based on the ingested data.
  • Sanitization: The script extracts content from specific HTML tags (title, meta, h1, p). While it parses the HTML structure, it does not sanitize the text content for malicious instructions that could influence an AI agent reading the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:33 AM