auto-claude Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• The skill relies on external services (Graphiti, Google API) for memory, which may introduce additional dependencies and potential data privacy considerations.
• Autonomous code execution, while isolated in a git worktree, still carries inherent risks if the user provides malicious or unintended instructions; the skill does not explicitly enforce additional sandboxing beyond the worktree.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• GitHub adoption: 95 GitHub stars
• Stars/forks activity: 95 stars, 23 forks; issue activity unavailable in current metadata
• Dependency/runtime risk: command execution surface, credential or environment access
• Permission surface: secrets or environment access, shell or command execution

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.