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.pyandlint_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.yamlandinternal-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