janitor-usage
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local shell script at ~/.claude/skills/skills-janitor/scripts/usage.sh to perform its analysis.
- [DATA_EXFILTRATION]: While the skill parses conversation history, no tools or commands for external data transmission were identified. Analysis results are stored in a local data/usage-history.json file.
Audit Metadata