vision Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• The SKILL.md references a SessionStart hook that is not part of the skill itself; this may confuse users if the hook is not installed.
• The script imports the openai package at module level, but the anthropic provider is lazily imported; this is fine but could be noted for clarity.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• Stars/forks activity: 170 stars, 8 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.