claude-md-overhaul

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses standard shell commands such as wc, ls, find, and grep to perform a multi-tier audit of file sizes, line counts, and project coverage across ~/.claude/ and ~/projects/ directories.
  • [COMMAND_EXECUTION]: Configures SessionStart and resume hooks within the agent's settings.local.json to automatically execute shell commands (e.g., cat ~/.claude/CURRENT.md) when a session is initialized.
  • [DATA_EXPOSURE]: Accesses and modifies local agent configuration files, including settings.local.json and CLAUDE.md, to manage skill overrides and update project memory indexing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 07:52 PM
Security Audit — agent-trust-hub — claude-md-overhaul