sync-rules

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a bundled Node.js script (scripts/sync-rules.mjs). This script is responsible for calculating file hashes, detecting local modifications (drift), and copying markdown files from the skill's directory to the project's .claude/rules/ directory.
  • [SAFE]: Analysis of the Node.js script confirms it only performs local file system operations (read/write/mkdir) within the project's scope. It does not perform any network requests or use dynamic code execution (like eval or exec) on untrusted data.
  • [SAFE]: The skill implements a secure workflow by using the AskUserQuestion tool to present an approval checklist to the user. This ensures that no files are added or updated without explicit human consent.
  • [SAFE]: Information gathering is limited to reading package.json and CLAUDE.md for technical stack detection, which is consistent with the skill's stated purpose of judging rule relevance.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:26 AM
Security Audit — agent-trust-hub — sync-rules