claude-usage-analyst Audit report.

Warnings

• Dependency or permission surface needs review
• Permission surface may require sandboxing
• SKILL.md uses a placeholder path `/path/to/claude-usage-analyst/scripts/analyze_claude_usage.py`, which will fail unless the agent resolves the actual skill directory.
• No sample output or test fixture is included, making it harder to verify the analyzer behaves correctly across environments.
• The skill instructs installing `ccusage` globally with npm, which requires appropriate user permissions; this is acceptable but should be called out as an environment-changing step.
• Quality score needs review
• Permission surface needs review: secrets or environment access, shell or command execution
• 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.