llm-friendly-site-architect

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide design guidance and generate reports for website architecture. It does not perform network operations, download external code, or access sensitive system files.
  • [COMMAND_EXECUTION]: The skill references local Python scripts for linting and validation (lint_production_skill.py and lint_skill_cluster.py). These are standard development tools within the project's environment and do not pose a security risk as they target local skill files.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill explicitly defines safety and privacy boundaries, instructing the agent to exclude admin paths, API keys, secrets, and private dashboards from any generated reports or configuration files.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests local metadata files like url-map.yaml and internal-link-graph.yaml. While this represents an attack surface for indirect injection, the risk is minimal as the output is restricted to architectural reports and the skill includes non-negotiable rules against generating hidden or deceptive content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 05:21 AM
Security Audit — agent-trust-hub — llm-friendly-site-architect