claude-code-usage-report

Pass

Audited by Gen Agent Trust Hub on May 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to read local JSONL files from ~/.claude/projects/ to calculate token usage. This behavior is transparently documented and aligns with the stated purpose.
  • [SAFE]: The bundled scripts (usage_report.py, check_pricing.py) use only Python's standard library. No external packages are required, and no remote code is downloaded or executed.
  • [SAFE]: Data remains local. The script generates a report that is printed to the console and saved to a local file (~/claude-code-usage-report.txt). No network operations were found that exfiltrate user data.
  • [SAFE]: The pricing update mechanism involves fetching data from the official Anthropic documentation (a well-known, trusted service) to verify and update the local pricing.json file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 21, 2026, 05:49 PM
Security Audit — agent-trust-hub — claude-code-usage-report