backend-architect

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide architectural guidance and generate documentation (Mermaid diagrams, ADRs). All instructions are well-structured and aligned with its stated purpose.
  • [SAFE]: The skill reads local project metadata files such as project-overview.md and tech-stack.md. This behavior is transparent and necessary for the agent to understand the existing system architecture before making design recommendations.
  • [SAFE]: No evidence of prompt injection, obfuscation, or unauthorized data exfiltration was found. The skill does not attempt to execute remote scripts or perform privileged system operations.
  • [SAFE]: Recommendations for technology stacks (e.g., FastAPI, Express, Spring Boot) are provided as architectural advice to the user and do not involve automated installation or execution of untrusted third-party packages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 10:46 AM
Security Audit — agent-trust-hub — backend-architect