llm-friendly-site-optimizer

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or persistence mechanisms were detected. The skill serves its stated purpose of website optimization.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of a local Python script (audit_llm_friendly_site.py) to perform site audits, which is standard functionality for this agent tool.
  • [EXTERNAL_DOWNLOADS]: The audit script fetches public content (HTML, robots.txt, sitemaps) from target URLs like mlllm.io to analyze metadata and citation readiness. These are intended network operations.
  • [PROMPT_INJECTION]: The skill processes external website content, which presents a surface for indirect prompt injection. \n
  • Ingestion points: HTML and text content fetched from target URLs in audit_llm_friendly_site.py. \n
  • Boundary markers: None; content is parsed and passed to the agent context. \n
  • Capability inventory: Includes local script execution and network fetching. \n
  • Sanitization: Limited to HTML parsing and whitespace cleaning.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:31 AM
Security Audit — agent-trust-hub — llm-friendly-site-optimizer