deepagents-architecture Audit report.

Warnings

• Permission surface may require sandboxing
• SKILL.md does not include explicit installation or dependency setup for the deepagents package.
• No security guidance is provided for FilesystemBackend root_dir permissions or subagent tool scoping.
• The skill lacks a clear 'Outputs' section describing the expected decision artifacts or recommendations produced.
• The middleware section appears incomplete or lacks examples for custom middleware ordering and configuration.
• Quality score needs review
• Permission surface needs review: secrets or environment access, filesystem or document access
• GitHub adoption: 80 GitHub stars
• Stars/forks activity: 80 stars, 8 forks; issue activity unavailable in current metadata
• Permission surface: secrets or environment access, filesystem or document access

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.