session-usage

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTION

Full Analysis

[DATA_EXFILTRATION]: The skill reads authentication tokens from ~/.claude/.credentials.json and the macOS Keychain via the security utility. It then transmits this token to the official Anthropic API endpoint (api.anthropic.com) to fetch current usage and limit data.\n- [COMMAND_EXECUTION]: The skill utilizes several shell commands, including security, jq, and https (httpie), to automate the retrieval and parsing of session usage information.

Audit Metadata

Risk Level

SAFE

Analyzed

Aug 5, 2026, 10:42 AM

Security Audit — agent-trust-hub — session-usage