skills/affaan-m/ecc/config-gc/Gen Agent Trust Hub

config-gc

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs standard shell utilities including find, grep, du, mv, and cp to perform filesystem audits and maintenance. These commands are restricted to the user's ~/.claude directory and are used for administrative tasks such as identifying orphaned scripts or creating backups before modifications.
  • [COMMAND_EXECUTION]: Utilizes jq to programmatically modify settings.json and settings.local.json to remove redundant permission entries. The skill includes safety best practices such as creating backups (.bak files) and logging changes to gc_log.md before performing these edits.
  • [SAFE]: The skill architecture explicitly mandates a 'human-in-the-loop' design, requiring individual confirmation for every proposed deletion and prohibiting autonomous or bulk actions. It implements a 'soft-delete' strategy by renaming or moving files to a temporary _gc_trash directory rather than performing permanent deletions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:47 PM
Security Audit — agent-trust-hub — config-gc