paperclip-org-builder

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill guides the user through a nine-stage organizational design process, storing intermediate state in a local JSON file (paperclip-org-draft.json). This workflow is transparent and does not involve any hidden operations.
  • [COMMAND_EXECUTION]: The skill utilizes local Python scripts (assemble-package.py, validate-draft.py, and validate-package.py) executed via uv run. These scripts perform standard file system operations, YAML generation, and data validation necessary for creating the organization's package structure.
  • [EXTERNAL_DOWNLOADS]: Stage 5 involves the discovery and addition of skills using the skills.sh ecosystem via the npx skills CLI. This is a legitimate integration with a well-known service for extending agent capabilities, and the instructions recommend sourcing skills from established organizations.
  • [DATA_EXPOSURE]: No evidence of sensitive data harvesting or exfiltration was found. The skill operates exclusively within the user-defined project directory and does not access sensitive system paths like SSH keys or environment variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 12:36 AM