audit-permission-grants

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled local shell script scripts/permission-rule-check.sh to perform the permission audit. This script utilizes standard system utilities such as find, grep, jq, awk, and tr to scan the repository's markdown files and configuration settings.
  • [DATA_EXPOSURE]: The audit process involves reading local configuration files, specifically .claude/settings.json and .claude/settings.local.json. The tool is designed with privacy in mind, as the script explicitly extracts only the permissions.allow array and contains logic to avoid echoing sensitive tokens or entire files to the output console.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — audit-permission-grants