workflow-builder

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill includes a dedicated validation script (scripts/validate_workflow.py) that enforces strict security boundaries by flagging the use of Node.js APIs (e.g., fs, require, process) and network calls (e.g., fetch) in the workflow orchestrator, ensuring sub-agents remain isolated.
  • [SAFE]: No external dependencies or remote code downloads were detected. All helper scripts are written using Python standard libraries and operate locally without network access.
  • [SAFE]: No evidence of obfuscation, hardcoded credentials, or persistence mechanisms was found across the 15 files analyzed. The skill's metadata accurately reflects its functionality.
  • [SAFE]: The skill handles indirect prompt injection risks by design, utilizing structured JSON schemas for agent communication and providing loops with mandatory budget/count guards to prevent runaway resource consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 06:57 AM
Security Audit — agent-trust-hub — workflow-builder