threejs-procedural-buildings-and-cities

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill is entirely focused on 3D geometry generation and architectural grammar.
  • [PROMPT_INJECTION]: The instructions in SKILL.md and references/grammar-and-mesh-compiler.md are purely technical and do not attempt to override agent behavior or bypass safety filters.
  • [DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or access to sensitive file paths were found in the scripts or documentation.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external code. The only script included (scripts/deterministic-placement-key.mjs) is a local utility module for generating deterministic IDs and rankings.
  • [COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:20 PM
Security Audit — agent-trust-hub — threejs-procedural-buildings-and-cities